OpenRig

What's new

Every change in each OpenRig release, with the pull request behind it.

Latest release

OpenRig 0.7.20

OpenRig 0.7.20 waits out a Claude usage limit and a lost tmux server. When a parked task's wake is refused because a Claude seat has hit its usage limit, OpenRig records why and retries at the reset Claude states; a Codex seat states no reset, so it keeps its ordinary retry. When the tmux server behind a seat goes away, the daemon pauses automatic delivery to that server's seats, checks back without starting the server, and offers the owed work again once it answers; rig status, rig ps and rig doctor report the outage. The rigs skill now opens with the consent rules your coding agent must keep, and tells it to read a handed-over task's result with rig queue show <id> --full. A workflow instance can be bound to one pod, and an opt-in throttle limits how often a Claude seat's status line is collected. Many fixes come from people using OpenRig.

2 added8 changed2 fixed

· 9 people thanked · Release notes

Highlights

  • ChangedWhen a waiting task's wake is refused because a Claude seat has hit its usage limit, OpenRig retries at the reset Claude states, and rig seat status shows a seat left at a bare shell as needing attention.

    When a parked row's wake is refused at a Claude seat that has reached its usage limit, the wake's record says so and retries at the stated reset; Codex states no reset, so a Codex seat's wake keeps its ordinary retry. A Codex seat's generation record is read from its declared home. rig seat status reads a seat left at a bare shell as needing attention, as rig ps does. rig daemon stop acts on a start reservation's child only after confirming the reservation still names it. Queue-only manual compaction prepares under the lifecycle lease. The draft guard recognizes its own collapsed paste. These change how recovery and delivery decide. This release doesn't claim a measured recovery improvement on a running team.

    #3508, #3507, #3515, #3447, #3465 · thanks @billbenettiLink

  • ChangedWhen the tmux server behind a seat goes away, the daemon pauses automatic delivery to that server's seats and offers the owed work again once it answers; rig status, rig ps and rig doctor report the outage. A community contribution.

    When the tmux server a seat depends on goes away, the daemon records it once and holds automatic delivery to that server's seats. It probes read-only every 5 s, backing off to 60 s, without starting the server, and offers owed work again when the server answers. An explicit rig send is still attempted. rig status, rig ps and rig doctor report the outage.

    #3448 · thanks @billbenettiLink

Before you upgrade 3

  • ChangedStop the daemon, back up its database, install 0.7.20, then restart it; your agents keep running. Back up and install only after rig daemon stop prints Daemon stopped.

    Run the upgrade in the environment that owns your daemon, keeping the same OPENRIG_HOME (legacy RIGGED_HOME) if you set it. Stop the daemon, back up its database, install the patch, then restart it. Your agents keep running; do not use rig down for this upgrade. If the daemon was started with --db, or with OPENRIG_DB (legacy RIGGED_DB) set differently from this shell, replace the DB= line below with that actual database path. Pass the same --db "$DB" to every rig daemon start, including recovery; rig config get db.path reads this shell's configuration, not the running daemon's launch arguments or environment. A failure stops the following commands; fix it before continuing. Back up and install only after rig daemon stop prints the line Daemon stopped: that is the stop outcome that confirms a clean shutdown. Its other success line, “No daemon target recorded; listener refused. Nothing to stop; prior drain not certified.”, means this stop has no recorded target. It does not prove that no daemon exists or that the last one shut down cleanly. A Daemon stopped from rig daemon status does not confirm a clean shutdown either. If the stop failed or had no recorded target, make sure the daemon is running on its original home and database (start it with rig daemon start --db "$DB" if rig daemon status does not say it is running), then run the whole block again. If the stop is still unconfirmed, use daemon-shutdown.json and daemon.log in your OpenRig home, together with rig context get help, to resolve the reported problem before retrying. Do not continue to the backup or install on an unconfirmed stop. A clean stop after restarting confirms only the new daemon’s shutdown, not whether earlier unfinished actions completed. Each stop replaces daemon-shutdown.json; look in daemon.log for earlier shutdown failures.

    Link

  • ChangedThree database updates apply at the first start, including the seat pool's storage whether or not you declare a pool. Going back to 0.7.19 after them isn't established, so keep the backup.

    Three additive migrations apply at the first start: 176_node_statusline_throttle (the status-line throttle setting), 177_workflow_bound_pod (a workflow instance's pod) and 178_seat_pool (the seat pool's storage). Migration 178 applies whether or not you declare a pool. Keep the backup: downgrading the migrated database to 0.7.19 is not established.

    Link

  • ChangedThe bundled openrig plugin is 0.7.20; openrig-core is 0.1.34.

    Bundled openrig is 0.7.20; openrig-core is 0.1.34.

    Link

Also in this release 6

A person's own agent 1

  • ChangedThe openrig-user skill says Claude Desktop picks up the team's work with a scheduled task in a fresh session, and the rigs skill can be added to OMP (Oh My Pi). A community contribution.

    The openrig-user skill says that Claude Desktop picks up the team's work with a scheduled task, in a fresh session, and that Monitor is for a session kept open. The rigs skill can be added to OMP (Oh My Pi), installing the shared skill only.

    #3503, #3509 · thanks @aryrabeloLink

Workflows, scope and status 2

  • AddedA workflow instance can be bound to one pod, a step that needs a receipt names --evidence-ref, and scope and proof default to the calling rig's project. A community contribution.

    A workflow instance can be bound to a pod. A workflow packet's Continuation line names --evidence-ref when its step needs a receipt, as rig workflow show does, and rig workflow route and rig workflow resume point to that exact command. Scope and proof default to the calling rig's project. Current-state progress updates carry a timestamp. An empty plan lock written with CRLF line endings is refused. Block notes are kept beside continuations.

    #3161, #3533, #3151, #3156, #3517, #3499 · thanks @dajiaohuang, @KayhuskLink

  • FixedOne workflow's unreadable mission no longer hides the attention view's other outcomes, and a renamed project keeps its tasks by its former ids. A community contribution.

    One workflow's unreadable mission no longer hides the attention view's other outcomes. A renamed project keeps its rows by its declared former ids, and rows no project claims are counted. Changes to files.allowlist and progress.scan_roots through the daemon's settings API are recorded on the event stream on a best-effort basis after saving; direct rig config set and rig config reset writes are not covered.

    #3492, #3267, #3373 · thanks @DeryFerdLink

Settings, seats and tools 3

  • AddedAn opt-in per-seat throttle limits how often a Claude seat's status line is collected, rig start can select fresh seats, and a settled Slack question card names the chosen option. A community contribution.

    An opt-in per-seat throttle limits how often the Claude status line is collected. rig provider bindings report what each seat is configured to use. rig start can select fresh seats. A settled Slack question card names the chosen option, redacted as the question card is.

    #3433, #3469, #3337, #3519 · thanks @billbenetti, @dajiaohuangLink

  • ChangedA model member can declare a seat-pool block, but nothing arms or dispatches a pool in this release, so declaring one changes no seat's behaviour. A community contribution.

    A model member can declare a seat-pool block, which is stored on its node, and a sizing planner exists for the pool. Nothing arms or dispatches a pool in this release: declaring one changes no seat's behaviour.

    #3480, #3478 · thanks @billbenettiLink

  • FixedTUI and CLI fixes: the TUI keeps its launcher running when its control socket fails, node rows line up by terminal width, and IPv6 targets work in rsync. A community contribution.

    The TUI degrades its control socket instead of ending the launcher, completes commands with leading whitespace, and measures health findings in terminal columns. The CLI aligns node rows by terminal column width, normalizes explicit daemon URLs, and brackets IPv6 targets in rsync operands. Mission and slice reads ask for the proof policy once per request, and slice-term matching runs in one pass; this release doesn't claim a measured speed-up.

    #3379, #3489, #3490, #3491, #3523, #3521, #3467, #3468 · thanks @DeryFerd, @Vaishnavi220506, @billbenettiLink

Known limits: 6 for this release. Read them
  • While a tmux server is gone, a stale probe observation can still release or reapply the delivery hold. Later observations correct it, with no guaranteed recovery time. The outage record is in memory, so a daemon restarted during a loss records it again.
  • A restore or rig start can label a Claude seat resumed before its conversation is confirmed, including when Claude reports that no conversation was found. A send can still land on Claude's workspace trust dialog. Check the seat's screen after a restore or start before relying on it.
  • A rig send message sent while Claude's AskUserQuestion dialog is open can become the answer to that question. This was observed on Claude Code 2.1.322 and 2.1.323 with both OpenRig 0.7.19 and 0.7.20.
  • Linked Codex configuration files keep version-specific hook-trust limits, as in 0.7.19. This release doesn't migrate existing noncanonical state or include the linked-path alias change. Review any hook prompt yourself; don't treat this upgrade as prior consent.
  • The seat pool's migration and stored block apply on upgrade even though nothing arms a pool.
  • A return route records where questions should go; it doesn't guarantee arrival. Choice prompts and other hosts keep their own paths.

Thanks 9

Thank you to everyone whose work is in this release: @aryrabelo, @DeryFerd, @Vaishnavi220506, @Kayhusk, @mvschwarz, @cavalcanticampos, @sn1thy, @dajiaohuang and @billbenetti.

Their contributions also improve the daemon's memory-limit reasons, tests, CI on Ubuntu, the custom-view SQL contract, Claude readiness polling, startup probing, and documentation.

Earlier releases

OpenRig 0.7.19OpenRig 0.7.19 lets fewer permission prompts go unseen, reports what an interrupted recovery skipped, and makes a failed start easier to recover. A permission prompt at a seat with no assigned work can now reach the same alerts as other prompts, and one is no longer hidden while a recovery waits directly on that seat. Restore reports a missing working folder or a skipped saved hook as a gap instead of quietly recreating the folder, and rig seat launch <seat> --fresh replaces a seat whose failed start left only an idle shell, without --stop. New and opt-in: the typing guard's queue-only mode keeps ordinary automatic notices out of a seat you type in, a hook bridge delivers messages to a Claude seat between turns instead of typing into its input box, and on Linux with systemd a seat can request a memory limit. Apps can also read the team's questions and answer them through a versioned interface. Many fixes come from people using OpenRig.5 added4 changed3 fixed

13 people thanked · Release notes

Highlights

  • FixedA permission prompt at a seat with no assigned work can now reach the same alerts as other prompts, and one is no longer hidden while a recovery waits directly on that seat.

    A permission prompt can reach the existing alert route even when its seat has no open work. A recovery waiting directly on that prompted seat or row no longer hides the prompt. Clears from an earlier occupant do not clear the current occupant's alert.

    #3425, #3446Link

  • FixedRestore reports a missing working folder or a skipped saved hook as a gap instead of quietly recreating the folder, and a recreated seat's notices and receipts now agree about which seat launched.

    Restore now reports skipped saved hooks and missing working folders as gaps. Restore's working-folder projection skips a folder confirmed absent; adapter home/state setup is separate. A fresh launch from a spec can still create its declared folder. Recreated seats' notices and receipts agree about which seat launched, and a delivered sequence can close its notice. Closure is best-effort if bookkeeping fails; a later sequence can still owe work.

    #3430, #3436, #3450, #3350, #3415Link

  • Fixedrig seat launch <seat> --fresh replaces a seat whose failed start left only an idle shell, without --stop, and can reopen a terminal server after a host restart once the old process is confirmed gone. A community contribution.

    launch --fresh can replace the shell left by a failed start without --stop. Fresh launch can reopen a terminal server after a host restart when the old process is confirmed gone. A missing tmux server is reported as a detached session, with guidance to restore or relaunch the seat; unavailable readings remain uncertain. Duplicate automatic watchdog registration no longer aborts startup.

    #3392, #3435, #3429, #3443 · thanks @Kayhusk, @cavalcanticamposLink

  • AddedFor a seat you type in, the typing guard's new queue-only mode keeps ordinary automatic notices out of its input; watchdog reminders go to the seat's queue instead. A community contribution.

    For a seat you type in, rig seat set-typing-guard <seat> --mode queue-only --reason <text> keeps ordinary automatic notices out of its input. Watchdog reminders can be noted on a matching row or recorded in a new queue row without a nudge; parked-owner reminders remain retained. Interrupted reminders survive daemon restart. Other delivery modes keep their own behavior.

    #3418, #3461 · thanks @billbenettiLink

  • AddedOpt-in for a Claude seat: a hook bridge delivers messages between turns instead of typing into its input box. A hook handoff isn't proof the agent read it.

    Claude hook delivery is opt-in: rig seat set-hook-bridge <seat> --enabled true --reason <text>, then inspect rig seat hook-bridge <seat>. On supported Claude versions, launch or restore installs the bridge; it takes messages only after this occupant's waiter has armed. Until then, ordinary typed delivery applies. If an already-routed bridge becomes unavailable, fallback follows the existing delivery checks and names why. The help's 20 seconds is not an arrival deadline: queued work, waiter state and the existing delivery checks determine waiting and fallback. A hook handoff is not proof the agent read or acted on it.

    #3270, #3445Link

Before you upgrade 3

  • ChangedStop the daemon, back up the database, install 0.7.19, then start the daemon again; your agents keep running through the restart. Run it with the same OpenRig home and database as the daemon you're upgrading.

    Run the upgrade in the environment that owns your daemon, keeping the same OPENRIG_HOME (legacy RIGGED_HOME) if you set it. Stop the daemon, back up its database, install the patch, then restart it. Your agents keep running; do not use rig down for this upgrade. If the daemon was started with --db, or with OPENRIG_DB (legacy RIGGED_DB) set differently from this shell, replace the DB= line below with that actual database path. Pass the same --db "$DB" to every rig daemon start, including recovery; rig config get db.path reads this shell's configuration, not the running daemon's launch arguments or environment. A failure stops the following commands. Fix it before continuing. If stopping failed, use rig daemon status: when it says “Daemon stopped”, continue from DB=; when it says “Daemon PID is absent”, start the daemon with its original home/database settings before retrying the block.

    Link

  • ChangedThree database updates add records for the hook bridge, each session's launch folder and app access. Going back to 0.7.18 after them isn't established, so keep the backup.

    Three additive migrations record the hook bridge, each session's launched folder, and app access. Keep the backup: downgrading the migrated database to 0.7.18 is not established.

    Link

  • ChangedThe bundled openrig plugin is 0.7.19; openrig-core is 0.1.33.

    Bundled openrig is 0.7.19; openrig-core is 0.1.33.

    Link

Also in this release 4

Questions and consent 1

  • ChangedThe installer's guidance keeps you in your own conversation unless you choose the operator's pane, and explains how to reload a skill added mid-session. It also says your answer covers that one prompt, not unrelated prompts later.

    The installer guidance keeps your conversation unless you choose the operator's pane, and teaches reloading a skill added during the session. The guidance says an answer covers that prompt, rather than permission to answer unrelated prompts later.

    #3423, #3431, #3454Link

Settings and connected tools 3

  • AddedOn Linux with systemd, a seat can request a memory limit next to its task limit, and rig seat status shows the limit it observed. A community contribution.

    On Linux with systemd, process_limits: { memory_max: "512M" } requests a per-seat memory limit alongside tasks_max; swap is separate. rig seat status shows the observed limit and counters. A limit that cannot be verified is reported, not silently claimed effective. Recovery may attempt a launch without a process limit, with a warning; that attempt can fail. An uncertain or already-started command is not repeated merely to obtain the limit.

    #3417 · thanks @billbenettiLink

  • AddedApps can read the team's questions, submit answers and recover receipts through a versioned interface. Its credentials identify an app and the people it may act for; they aren't personal logins. A community contribution.

    Apps can use the versioned human-answer interface to read questions, submit answers and recover receipts. Credentials identify an app and permitted actors; they are not private per-person logins. Other improvements bind external input to its run, add optional webhook signatures, and pass advisory participant fields through rig_team.

    #3426, #3420, #3364, #3396, #3410 · thanks @smotaLink

  • AddedOn runners that support it, rig seat cancel asks to stop one exact turn and reports what happened; raw Claude and Codex terminal seats don't get it. A community contribution.

    Capable runners offer rig seat cancel <seat> --run-id <run> --native-turn-id <turn> --request-id <id> for the exact target from rig seat status <seat> --json. Inspect its requested, cancelled, not-this-turn or not-supported result. Neither permission withdrawal nor an accepted cancellation request proves the operation stopped; raw Claude/Codex TUI seats do not gain this runner capability.

    #3364 · thanks @smotaLink

Known limits: 6 for this release. Read them
  • A later unreadable tmux sample can show recorded running again after an earlier stopped reading. “Liveness unconfirmed” is not evidence of a live process; inspect the seat before relying on that label.
  • Linked Codex configuration files retain version-specific hook-trust limits. This release does not migrate existing noncanonical state or include the linked-path alias change wholesale. Review any hook prompt yourself; do not treat this upgrade as prior consent.
  • Queue-only reminders are not exactly-once: a lost note receipt can repeat a note. Check the row before acting twice.
  • Downgrading past the Claude hook exec change can leave generated settings unrecognized by the older daemon. Keep your settings backup and inspect them before restarting an older release. (#3427)
  • Manual compaction preparation can be held at queue-only. Inspect rig compact <seat> --state and rig seat held-messages <seat> before deliberately choosing an existing delivery route or level; changing the level does not replay retained messages.
  • A return route records where questions should go; it does not guarantee arrival. Choice prompts, foreign or conflicting routes, existing delivery custody, and a relay that cannot be made keep their existing paths. Tasks at a conversation's address are read on its next turn. When checking open routed tasks, include blocked rows: OPENRIG_SESSION_NAME='<recorded address>' rig queue list --owned --state pending,in-progress,blocked.

Thanks 13

Thank you to everyone whose work is in this release: @DeryFerd, @Vaishnavi220506, @Kayhusk, @EZotoff, @Aummadour, @mvschwarz, @Nikhi00718, @cavalcanticampos, @smota, @sn1thy, @dajiaohuang, @billbenetti and @dependabot.

Their contributions also improve terminal column sizing, JSON errors, transcript searches, workflow ownership, account-label display, scope links, cleanup and documentation.

OpenRig 0.7.18OpenRig 0.7.18 can send your team's prompts back to the conversation you handed the work over from. Hand work over with rig queue create --return-route auto, and when the team stops at a prompt that isn't a choice menu, it comes back to your conversation as a task on your next turn. Nothing wakes an idle conversation, arrival isn't guaranteed, and neither of this release's first-user runs met all its criteria. Restore no longer counts a seat it left as a bare shell as running in rig ps, and three opt-in settings can now be chosen per seat: native input, Claude's auto mode and, on Linux with systemd, a task limit. Many fixes come from people using OpenRig.3 added9 changed5 fixed

16 people thanked · Release notes

Highlights

  • Addedrig queue create --return-route auto gives the conversation you hand work over from an address, so a seat's prompt that isn't a choice dialog comes back to it as a task; it arrives on that conversation's next turn, and arrival isn't guaranteed.

    Hand a goal over with a return route: rig queue create --return-route auto gives your conversation an address, and every handoff carries it (--return-route self from a session that joined the team). When routed work is held at a seat's prompt, or waits on it, a prompt that isn't a choice dialog is sent to that address as a task. Choice prompts, a prompt already with the gateway, and a route that can't be used (another host's, two that disagree, or a relay that couldn't be made) keep their existing path. The rigs skill teaches this; without --return-route, nothing changes.

    #3318Link

  • FixedA seat that restore leaves as a bare shell no longer counts as running in rig ps, and the agent responsible for it gets one task per restore listing each cause and the next step.

    A seat that restore leaves as a bare shell no longer counts as running in rig ps, including a recreated seat, and a seat with a delegation parent or escalation destination gets that owner one queue item per restore listing each cause and the next step. Launching over a live session no longer says "Already running".

    #3185, #3216, #3366, #3215Link

  • AddedThree per-seat settings, all opt-in: native input instead of terminal typing, Claude's auto mode, and on Linux with systemd a task limit. A community contribution.

    Per-seat choices, all opt-in: native input instead of terminal typing (rig seat set-input-route <seat> --route native --reason <text>); Claude's autoMode block (claude_auto_mode, or rig seat set-permissions --auto-mode); and, on Linux with systemd, a requested task limit (process_limits: { tasks_max: N }). A fresh start whose limit isn't seen to take effect is refused; a recovery that can't apply it may try without the limit, with a warning; and an uncertain start is reported and not retried. An export names a stored limit it can't read instead of refusing the rig.

    #3339, #3286, #3332, #3390 · thanks @smota, @Temikus, @billbenettiLink

  • ChangedSlack: a button answer keeps each option's history and who gave it, settled cards drop the raw closure code, and rig slack manifest --private-channel sets up a private channel. A community contribution.

    Slack: a button answer keeps each option's history and who gave it; a click that fails to record enters the existing retry path, which fills only a still-unanswered question. Settled cards drop the raw closure code ("Denied" for a refusal), and the opt-in rig slack manifest --private-channel sets up a private channel. An answer through MCP's rig_question_answer is accepted when the daemon requires an operator token.

    #3353, #3359, #3324, #3344, #3257 · thanks @Aummadour, @billbenetti · reported by @z4ccLink

  • FixedAfter OpenRig's home moves, rig up --existing --cwd restores into the folder you name, and Claude seats keep OpenRig's core plugin.

    Restoring after OpenRig's home moved: rig up --existing --cwd honors --cwd, names a missing saved folder and leaves a folder with a declared project unscaffolded, and Claude seats keep OpenRig's core plugin.

    #3347, #3352Link

Before you upgrade 3

  • ChangedStop the daemon, back up the database, install 0.7.18, then start the daemon again; your agents keep running through the restart. Run it with the same OpenRig home and database as the daemon you're upgrading.

    Stop the daemon, back up the database, install 0.7.18, then start the daemon. Your agents keep running through a daemon restart; don't use rig down, which ends them. Each step runs only if the one before it succeeded. The backup goes to a new, dated file, with its -wal file beside it when there is one, so running the block again never overwrites an earlier backup. If you installed OpenRig another way, use that in place of the npm install line. Before running the block or any recovery command, use the same OpenRig home (OPENRIG_HOME, or legacy RIGGED_HOME) as the daemon you are upgrading. If that daemon was started with --db, or with OPENRIG_DB (legacy RIGGED_DB) set differently from this shell, replace the block's DB= line with its actual database path instead of using rig config get db.path, and pass that path with --db to every rig daemon start below, including recovery. The config command reads this shell's configuration, not the running daemon's launch settings. If a step fails, nothing after it runs: fix what it reports, then run the whole block again. If rig daemon stop fails and rig daemon status then says "Daemon stopped", run the block from the DB= line. If it says "Daemon PID is absent", run rig daemon start, then the whole block again. Keep the backup, and its -wal file, until 0.7.18 is running well.

    Link

  • ChangedFour database updates run before the daemon listens. Going back to 0.7.17 after them isn't established, so keep the backup. A community contribution.

    Four migrations run before the daemon listens (two numbered 171, then 172 and 173), each adding columns or indexes. Going back to 0.7.17 after them isn't established; keep the backup.

    #3286, #3339, #3318, #3332 · thanks @Temikus, @smota, @billbenettiLink

  • ChangedThe openrig plugin carries 0.7.18, and openrig-core moves to 0.1.32.

    The plugins: openrig carries 0.7.18, and openrig-core moves to 0.1.32 because its skills and refocus hook changed.

    Link

Also in this release 9

Your team's questions, in your own conversation 1

  • ChangedThe kernel operator is instructed to answer a registered person where they wrote, and messaging-the-human says how to close the question an answer settles.

    Guidance: the kernel operator is instructed to answer a registered person where they wrote, without the terminal user's leave (guidance, not proof an answer is delivered), and messaging-the-human says how to close the ask an answer settles.

    #3370, #3305Link

Recovering the same work 3

  • ChangedRestore and restore-check name agents that share a recorded conversation and leave the choice to you; --plan shows each seat's restore permission. A community contribution.

    Restore and restore-check name agents that share a recorded conversation and leave the choice to you; --plan shows each seat's restore permission and its source.

    #3250, #3186 · thanks @billbenettiLink

  • Fixedrig seat handover --recover reads an interrupted Claude handover more truthfully and accepts a successor alone in its session's current window. A community contribution.

    rig seat handover --recover reads an interrupted Claude handover more truthfully and accepts a successor alone in its session's current window.

    #3246, #3369 · thanks @billbenettiLink

  • FixedA later rig down no longer exits 2 over a released session's kept skills, Codex 0.167.1 and 0.167.2 seats show their real activity, and refocus orients from the seat's project when no task is in progress. A community contribution.

    Also: a later rig down no longer exits 2 over a released session's kept skills (a plain down of a stopped rig still exits 1); Codex 0.167.1 and 0.167.2 seats read their real activity; an adopted, still-running seat's hooks read as its own; and refocus orients from the seat's selected project when no task is in progress.

    #3303, #3182, #3365, #3351 · thanks @cavalcanticampos · reported by @KayhuskLink

Queue, delivery and settings 4

  • Addedrig compact on a Pi seat now asks Pi to compact itself, and --state reports the attempt. A community contribution.

    rig compact on a Pi seat requests Pi's own compaction, and --state reports the attempt.

    #3013 · thanks @EZotoffLink

  • Changedrig queue tag adds tags to an existing task, rig queue list names a handed-off task's successors, and a wake that failed before any input gets one retry. A community contribution.

    Queue and workflows: rig queue tag adds tags to an existing row; rig queue list names a handed-off row's successors; a handoff advises on a mission or slice tag that resolves to nothing; a hold blocked on a custom-ID row records its wake; a wake that failed before any input gets one retry on the same seat; and rig workflow route adopts a second handoff to the same target.

    #3281, #3302, #3178, #3152, #3243, #3311, #3363 · thanks @EZotoff, @Aummadour, @dajiaohuang · reported by @billbenetti, @parkingmeterLink

  • ChangedRunner reports stay bound to their run, and recent transitions honour a limit up to 1,000; this release makes no speed claim. A community contribution.

    Also: runner reports stay bound to their run, recent transitions honour a limit up to 1,000, and the stuck sweep makes fewer reads. This release makes no speed claim.

    #3150, #3211, #3301, #3340 · thanks @smota, @shravansumanthanan · reported by @ziadehLink

  • FixedTerminal fixes: a custom TMUX_TMPDIR is named in the attach command, a herdr-app cell at herdr's default hidden size no longer resizes its seat, and rig acp run's log keeps multibyte characters whole. A community contribution.

    Terminals and assistants: CLI terminal reads send the configured terminal bearer; a custom TMUX_TMPDIR is named in the attach command; with tmux 3.2 or later, a herdr-app cell at herdr's default hidden size (200x120) no longer resizes the seat; tmux credential cleanup can't fall back to a server-wide value; rig acp run's log keeps multibyte characters split across reads; and network assistants learn the retry rule and pickup timing.

    #3360, #3165, #3358, #3342, #3343, #3329 · thanks @smota, @dajiaohuang, @w4rc0n, @pr0xc3nt4ur1, @oodadoudouLink

Behaviour that changed 1

  • ChangedEach restored seat's checkpoint is now its own file, .rigged-checkpoint-<session>-<digest>.md; anything that reads .rigged-checkpoint.md won't find it.

    Each restored seat's checkpoint is its own file, .rigged-checkpoint-<session>-<digest>.md; anything that reads .rigged-checkpoint.md won't find it.

    #3347Link

Known limits: 8 for this release. Read them
  • Prompts in your own conversation wait for you: a routed prompt arrives on that conversation's next turn, nothing wakes an idle one, and arrival isn't guaranteed. A prompt can still change between OpenRig reading it and sending your key. In two measured Claude first-user runs, one agent set no return route. The other completed reviewed, committed work with the route set, but read prompt relays only after the prompts had been answered and approved later prompts beyond the person's one-time consent. Neither run met all first-user criteria.
  • Adding rigs during a running Claude Code session: If installation creates a top-level skills directory that was absent when the session started, Claude Code's documentation says to use /reload-skills (available from Claude Code 2.1.152) to discover it. Starting a new session is an alternative. Neither recovery was exercised in this release's first-user test.
  • Restore: a seat isn't told where its checkpoint file is, and a written checkpoint isn't proof it was read. After a --cwd restore, rig down doesn't clean OpenRig's Claude settings, hooks and collector from that folder. When a full restore recreates a seat, its result can still list it as not started, and the attempt's record can miss its actual outcome.
  • Native input route: withdrawing a permission doesn't cancel a native seat's work in progress.
  • Queue help says a human seat such as human@host asks no one; that holds only for an unregistered one.
  • Linked Codex config files: when a Codex seat's config.toml or hooks.json is a symbolic link, OpenRig records its hook trust under the link's target, as in 0.7.14. A change to key it by the file's own name isn't in this release, and such a seat may be asked to review hooks again. With a linked config.toml, OpenRig can also miss a setting stored for it that turns OpenRig's hooks off, and set those hooks up anyway when it moves them into hooks.json. (#3078)
  • OpenRig 0.7.17 rejects teams whose exported rig.yaml contains claude_auto_mode or process_limits. Upgrade the receiving install to 0.7.18, or remove those fields from a copy only if you intend to share without those per-seat settings.
  • From 0.7.17: its known limits still apply, except the bare-shell count, the second rig down's exit 2 and Codex 0.167.1 and 0.167.2's unknown (#3185, #3303, #3182).

Thanks 16

Thank you to everyone whose work is in this release: @Aummadour, @billbenetti, @cavalcanticampos, @dajiaohuang, @DeryFerd, @EZotoff, @oodadoudou, @pr0xc3nt4ur1, @shravansumanthanan, @smota, @Temikus and @w4rc0n.

Thanks also for the reports behind these fixes: @billbenetti (#2725, #3218, #3316), @Kayhusk (#3320), @parkingmeter (#1933), @z4cc (#313) and @ziadeh (#2487).

OpenRig 0.7.17OpenRig 0.7.17 is a polish release. Restore now says when it skipped an agent that wasn't in the snapshot, or left one attached, instead of reporting everything restored, and rig down releases a session OpenRig adopted rather than started, leaving it running instead of failing. OpenRig's installer, kernel operator and rigs skill are also now told to bring a team's questions into the Claude Code conversation you started it from, when you stay in that conversation; in this release's first trial, it didn't complete that journey. There are fixes across delivery, workflows and connected agents, including contributions from people using OpenRig.2 added12 changed8 fixed

4 people thanked · Release notes

Highlights

  • ChangedRestore now says when it skipped a seat that wasn't in the snapshot's roster, or left one attached: the rig reads partially_restored.

    Restore says when it didn't restore everything: a seat skipped because it isn't in the snapshot's roster, or left attached, makes the rig read partially_restored. An adopted seat keeps a usable recorded session name; otherwise restore names the old and new address.

    #3260Link

  • Fixedrig down now releases a tmux session OpenRig adopted rather than started, leaving it running, instead of failing.

    rig down releases a claimed tmux session (self-attached inside tmux, adopted, bound or reconciled) instead of failing: it prints Released, not stopped: <session>, leaves the session running and exits 0. An external CLI attachment is unchanged on down, and rig remove of one no longer fails with 409 kill_failed.

    #3263, #3272Link

  • ChangedWhen you stay in your own Claude Code conversation, the installer and the kernel operator are instructed to bring a seat's prompt to you there, with its choices word for word. In this release's first trial, it didn't complete that journey.

    When you stay in your own Claude Code conversation, the installer is instructed to hand your goal to the team as a task from it. The kernel operator is instructed to bring a seat's prompt there with its choices word for word, and to offer a seat's terminal only if you choose to watch or answer in the pane. If you chose the panes, nothing changes.

    #3288, #3306Link

  • FixedDraft-aware delivery reads an empty input box as empty under Claude Code 2.1.322 and 2.1.323's wide paste hint and update-failure footer.

    Draft-aware delivery reads an empty input box under Claude Code 2.1.322 or 2.1.323's wide paste hint and auto-update failure as empty (checked with Claude Code 2.1.322 and 2.1.323 in a test run).

    #3231Link

Before you upgrade 3

  • ChangedStop the daemon, back up the database, install 0.7.17, then start the daemon again; your agents keep running through the restart. The backup now goes to a new, dated file each time.

    Stop the daemon, back up the database, install 0.7.17, then start the daemon. Your agents keep running through a daemon restart; don't use rig down, which ends them. Each step runs only if the one before it succeeded. The backup goes to a new, dated file, with its -wal file beside it when there is one, so running the block again never overwrites an earlier backup. If you installed OpenRig another way, use that in place of the npm install line. If a step fails, nothing after it runs: fix what it reports, then run the whole block again. If rig daemon stop fails and rig daemon status then says "Daemon stopped", run the block from the DB= line. If it says "Daemon PID is absent", run rig daemon start, then the whole block again. Keep the backup, and its -wal file, until 0.7.17 is running well.

    Link

  • ChangedTwo database updates run before the daemon listens. Going back to 0.7.16 after them isn't established, so keep the backup.

    Two migrations run before the daemon listens (168 and 170). Going back to 0.7.16 after them isn't established; keep the backup.

    #3260Link

  • ChangedThe openrig plugin carries 0.7.17; openrig-core stays 0.1.31.

    The plugins: openrig carries 0.7.17; openrig-core stays 0.1.31.

    Link

Also in this release 15

Your team's questions, in your own conversation 1

  • ChangedThe launch plan says when a seat with no permission policy gets the team default, and every seat's startup text is smaller. A community contribution.

    Also: the launch plan says a team seat with no permission policy gets the team default, and every seat's startup text is smaller, with the installing procedure loaded from the rigs skill when needed.

    #3289, #3238 · thanks @KayhuskLink

Recovering the same work 3

  • AddedTwo opt-in daemon routes: resume one saved original conversation, and hold a rig's automatic delivery during maintenance.

    Two opt-in daemon routes: resume one banked original conversation, and hold one rig's automatic delivery during maintenance until an explicit end. See docs/reference/daemon-http-clients.md.

    #3260Link

  • FixedA restore that can't confirm it stopped a blank session now keeps its record and says the session may still be running.

    A restore that can't confirm it stopped a blank session keeps that session's record and binding, reads attention_required, and says the session may still be running: check it with rig capture and stop it with rig seat stop.

    #3258Link

  • FixedDuring a Claude resume, a pane that moves while its resume token is captured leaves the token unknown.

    Claude resume: a pane that moves during resume-token capture leaves the token unknown.

    #3262Link

Delivery, workflows and tools 9

  • Addedrig workflow revise can drop an obsolete required order from unstarted work, and a replayed route adoption without --packet writes nothing.

    Workflows: rig workflow revise can drop an obsolete required order from unstarted work, and a replayed route adoption without --packet writes nothing.

    #3276, #3266Link

  • ChangedThree daemon read paths do less repeated work; this release makes no speed claim.

    Three daemon read paths changed: the stuck sweep yields between windows of undelivered work, Codex thread lookup reuses new log rows on warm reads, with full cold and fallback reads, and a work node's SPEC.md is reread only when its file changed, within a two-second settle window, or when that can't be read. This release makes no speed claim.

    #3285, #3295, #3296Link

  • ChangedRefusals at a model picker (close it with Esc) and under managed disableSideloadFlags now say what to do.

    Clearer refusals at a model picker (close it with Esc) and under managed disableSideloadFlags.

    #3207, #3247 · reported by @DavKatoLink

  • ChangedWork for a hosted member with no wake trigger reads awaiting-pickup: instead of unroutable:, because it waits until the member reads its queue.

    Work for a hosted member with no wake trigger reads awaiting-pickup: instead of unroutable:: it waits in its queue until the member reads it.

    #3222Link

  • ChangedConnected agents and tools: rig_queue_show labels who acted, the TUI can read a remote rig's seats, Pi and OMP runner panes name their model, and rig bundle check reports invalid configuration names. A community contribution.

    Assistants and tools: an external connection's rig_queue_show labels who acted apart from the reader; the TUI can read a remote rig's seats with ui.topology_remote_seats (off by default); a Pi or OMP runner pane names its model and state; rig bundle check reports schema-invalid configuration names; and the text output of rig network status hides a hub URL's query (--json is unchanged).

    #3234, #2922, #3212, #3160, #3207 · thanks @EZotoff, @dajiaohuangLink

  • FixedAn ordinary send is refused while Claude's question dialog is open, in the layouts OpenRig recognizes; its own tests show this, and it isn't yet checked with Claude Code itself.

    Claude's question dialog, in the several-question, editor-shortcut and preview layouts OpenRig recognizes, refuses an ordinary send (shown by its tests; not yet checked with Claude Code itself).

    #3256Link

  • FixedA resumed Codex conversation isn't told to sign in again because of an old token-refresh failure.

    A resumed Codex conversation isn't told to sign in again because of an old token-refresh failure that newer output follows.

    #3248Link

  • Fixedrig provider switch --token-file keeps the Claude token step for pane readings it used to drop.

    rig provider switch --token-file keeps the Claude token step for pane readings it used to drop, and after a failed correction only for a session proven to be this seat's.

    #3278Link

  • FixedFixes for account-rig erasure, OpenShell recreation after a socket change, and handoff reconciliation hints.

    Also: account-rig erasure, OpenShell recreation after a socket change, and handoff reconciliation hints.

    #3190, #3291, #3217Link

Behaviour that changed 2

  • ChangedWhen nobody is registered as the team's person, delivery reads undeliverable:no-registered-human.

    An empty person registry reads undeliverable:no-registered-human.

    #3288Link

  • Changedrig send --dangerously-interact without --type-without-checking now stops on a person's text under Claude Code's wide footer row; its own tests show this, and it isn't yet checked with Claude Code itself.

    rig send --dangerously-interact without --type-without-checking stops on a person's text under Claude Code's wide footer row (shown by its tests; not yet checked with Claude Code itself).

    #3231Link

Known limits: 10 for this release. Read them
  • Questions in your own conversation wait for you: nothing wakes an idle conversation, and a prompt that changes between OpenRig reading it and sending your key can take the key. In this release's first trial, with Claude Code and a simulated person, a reviewer's permission question never reached the person, the person's agent twice offered a bare terminal attachment as a way to answer a seat's prompt, and the work didn't reach a reviewed commit. No return address for the person's conversation had been established, and no escalation for the reviewer's question was recorded. This guidance doesn't reliably complete that journey, and a second trial wasn't run.
  • Restore: restore-check's recovery plan still counts seats restore leaves alone, and a seat left as a bare shell after "Harness not started" still counts as running in rig ps.
  • rig down: a second down while a released session runs reports its kept skills as an error and exits 2. After rig down --delete, a later down of another rig in the same folder may remove OpenRig's shared guidance there.
  • A Codex seat resumed on Codex 0.167.1 or 0.167.2 can read unknown when its resume header or update notice names that version.
  • rig scope and rig proof can't be limited to a rig's own project. (#3026)
  • Reading queue state with rig queue list: the median time was about 22% (about 90 ms) slower than 0.7.16 in a matched test on a pre-release build. The cause wasn't found, and the final build wasn't re-measured.
  • Linked Codex config files: when a Codex seat's config.toml or hooks.json is a symbolic link, OpenRig records its hook trust under the link's target, as in 0.7.14. A change to key it by the file's own name isn't in this release, and such a seat may be asked to review hooks again. With a linked config.toml, OpenRig can also miss a setting stored for it that turns OpenRig's hooks off, and set those hooks up anyway when it moves them into hooks.json. (#3078)
  • Approvals your agent recorded: in one Claude setup, an agent recorded approvals it made itself as "Person approved"; check the conversation to see who decided.
  • Slack buttons: in 0.7.16's tests, an answer given by button wasn't seen to reach OpenRig, and the cause isn't known. Type the reply instead.
  • From 0.7.16: its known limits still apply unless this release changes them (#3231, #3260).

Thanks 4

Thank you to everyone whose work is in this release: @dajiaohuang, @EZotoff and @Kayhusk.

Thanks also for the reports behind these fixes: @DavKato (#3245) and @Kayhusk (#3228).

OpenRig 0.7.16OpenRig 0.7.16 makes a first team easier to get running and its work easier to recover. When a new teammate stops at a permission or trust prompt, OpenRig's rigs skill now has your coding agent show you the prompt as a question, send your choice and get the teammate going again, rather than answering for you, and picking the standard permissions no longer brings more prompts than picking none. An upgrade now keeps OpenRig's recovery skills, rig seat handover --recover adopts the running successor of a failed Claude handover, and a message to an agent that doesn't exist is kept and reported as "Recorded, not delivered" instead of only failing. There are fixes across delivery, workflows and connected agents, many from people using OpenRig.12 added18 changed12 fixed

8 people thanked · Release notes

Highlights

  • ChangedWhen a seat stops at a permission, trust or hook-review prompt, the rigs skill now tells the coding agent you're working with to bring it to you as a question, instead of answering it itself.

    The rigs skill tells a person's own agent to bring a seat's permission, trust or hook-review prompt to them as a question by default, instead of answering it itself. It tells the agent to show the prompt, capture the seat again before sending, and send the digit or letter the screen shows for their choice, never their words, and to ask when the screen shows no key. A yes to one prompt isn't a yes to the next, a "don't ask again" choice is picked only when they picked it, and an instruction they gave outright lets the agent decide that kind of prompt within what they said. The agent is told never to record its own answer as the person's. The getting-started guide names each authentication, trust, hook-review or permission prompt as the person's to answer before that seat gets work.

    #3206Link

  • ChangedChoosing the built-in standard or open policy for a seat now keeps the team's default allowances, so it no longer brings more permission prompts than choosing nothing.

    A seat whose effective policy is the built-in standard or open keeps the team launch default, as a seat with no policy does. Any recorded policy used to turn the team default off, so choosing standard brought more prompts than choosing nothing: ordinary rig reads, git reads and tests all asked. The member's policy decides over the rig's. An explicit seat permission choice, a Codex envelope or named Codex profile, a Claude seat's own rules, none, locked, custom, auto and yolo, and kernel, Pi and terminal seats keep their meaning. This keeps the team default; it doesn't apply the whole policy, and a seat that keeps it can still ask before the project's own commands (see Known limits). The Claude team default includes ask rules for lifecycle commands such as rig up and rig down. The Codex team default does not add equivalent per-command ask rules; native settings and explicit permission choices still apply. The launch plan now says whether a seat gets the team default's allowances, instead of a bare launch_posture=floor. OpenRig can't see rules applied in project or user native settings files; those seats keep the team default alongside them, and keeping it doesn't loosen those rules.

    #3230Link

  • FixedAn upgrade now keeps OpenRig's packaged recovery skills, such as claude-compaction-restore, current when a seat comes back with rig up --existing; copies you edited stay as they are. It's tested at the unit and source level.

    An upgrade keeps OpenRig's packaged recovery skills. After rig down, an upgrade and rig up --existing, a seat's own unedited copies of OpenRig's packaged skills, such as claude-compaction-restore and seat-continuity-and-handover, come back at the current packaged contents. Before, a packaged skill whose bytes changed in the upgrade wasn't put back: the restore named it missing, and the seat came back without it. When the upgrade came before rig down, the copy used to stay at the earlier version; it's brought up to date now. An edited copy (its bytes or a file mode), a file OpenRig didn't write and a copy recorded from another source stay as they are, and the restore names each. A skill the seat's profile selects itself keeps its own restore policy. Other plugins' skills aren't changed. It's tested at the unit and source level; see Known limits.

    #3279Link

  • Addedrig seat handover <seat> --recover adopts the running successor of a failed handover for a Claude seat, instead of leaving the seat with its old agent; it hasn't yet been tried on a real failed handover. A community contribution.

    rig seat handover <seat> --recover adopts the running successor of a failed handover, instead of leaving the seat with its retiring occupant. Recovery is for Claude seats: it proves the successor's process and identity from the failed attempt's record, then records the conversation that process holds now as the seat's resume target. When that conversation can't be read, the conversation its launch named is recorded instead, with a warning that a /clear before the recovery would make it stale. Four results are new, all only on --recover: no_handover_to_recover, handover_attempt_superseded, recover_runtime_unsupported and successor_identity_unproven. Recovery from a real failed handover wasn't checked when this release was tested.

    #3044 · thanks @billbenettiLink

  • ChangedA message or task sent to a seat that doesn't exist is now kept instead of only failing, and the CLI says "Recorded, not delivered".

    A send or row to a missing destination is kept and says so. A queue row whose rig or seat is absent keeps its exact address, with a destination advisory (destination_status, or unmatched_destination_seat for a missing seat in a known rig): missing, archived, hosted or unknown. A direct send that finds no receiver keeps the message in the sender's outbox; the CLI prints "Recorded, not delivered", --verify exits nonzero, and rig walk stops there. No forwarding, retry or reassignment is added.

    #3142Link

Before you upgrade 3

  • ChangedStop the daemon, back up the database, install 0.7.16, then start the daemon again; your agents keep running through the restart.

    Stop the daemon, back up the database, install 0.7.16, then start the daemon. Your agents keep running through a daemon restart; don't use rig down, which ends them.

    Link

  • ChangedTwo database updates run before the daemon listens. Going back to 0.7.15 after them isn't established, so keep the backup. A community contribution.

    Two migrations run before the daemon listens. Migration 167 adds seat_handover_attempts (for rig seat handover --recover), and migration 169 adds seat_runtime_home_records (for rig seat record-runtime-home). Going back to 0.7.15 after them isn't established; keep the backup.

    #3044, #3220 · thanks @billbenettiLink

  • ChangedThe openrig plugin carries the CLI's version, 0.7.16, and openrig-core moves to 0.1.31.

    The plugins: the openrig plugin carries the CLI's version, 0.7.16. openrig-core moves to 0.1.31, because its skills changed.

    Link

Also in this release 34

A person's first team 4

  • AddedAfter you answer a prompt a new seat stopped at, the rigs skill tells the agent you're working with to run the rig seat continue command the seat shows, so it gets its startup instructions in the same conversation.

    After the person answers a prompt a seat stopped at while starting, the rigs skill tells their agent to check rig ps --nodes again and, when it shows Startup details (<seat>) ending in rig seat continue <seat>, to run that command, which delivers the seat's startup instructions in the same conversation. When the person's choice is Escape, it tells the agent to send the key itself (rig send <seat>@<rig> $'\e' --dangerously-interact --reason "…"), which is sent once, with no Enter added, and to repeat the prompt check while it waits for a seat's result.

    #3271Link

  • AddedAn agent on an external grant now sees the team and its members by the names you know them by.

    A person's assistant on an external grant sees the team by the name the person knows it by, and its members by their roster label. The team's name comes from the rig's network roster or, when there's none, from the roster that declares the rig. A label over 200 characters, or with control characters, line or paragraph separators, bidirectional embeddings, overrides or isolates, certain invisible formatting characters, or angle brackets, is set aside with label_problem; the member and the roster still load.

    #3221, #3249Link

  • AddedThe rigs skill teaches the agent that installed OpenRig for you to keep its own return address, so the team's questions come back to it.

    The rigs skill's setup path teaches an assistant that installed OpenRig for a person, and that they keep talking to, to keep its own return address, so the team's questions come back to it and it answers them with the person's exact words.

    #3134Link

  • ChangedOpenRig's MCP instructions now tell an agent to list the team and ask which teammate you mean when more than one could be, instead of guessing.

    OpenRig's MCP instructions tell the assistant to list the team and ask which assistant a person means when more than one could be, instead of picking one from its own history. rig mcp serve --front-door says a request is picked up on its own only by a running team seat.

    #3179Link

Recovering the same work 7

  • Addedrig seat runtime-home shows which runtime home a seat's next launch uses, and rig seat record-runtime-home records the one its existing conversation lives under, with no relaunch.

    rig seat runtime-home <seat> shows the runtime home (Claude Code's config directory or a Codex home) the seat's next launch uses. rig seat record-runtime-home <seat> --home <abs> --expect-occupant <gen> --expect-original <id> --expect-revision <n> --reason "<why>" records the one its existing conversation lives under, with no successor, relaunch or manual database edit. Recording sets the home used by the seat's next launch. A later explicit home change is retained; restoring a selected conversation shows and applies the home selected for that original. A stale expectation returns runtime_home_conflict and applies nothing. The result reports whether the home is present and whether the original conversation is found there, and reports the running process as unverified.

    #3220Link

  • ChangedWhen managed restore fails for a seat that no other agent hands work to, the notice now goes to the receiving agent or the kernel operator, then to a registered person.

    When managed restore or preparation fails for a seat with no independent delegation parent, the recovery notice goes to the receiving agent or kernel operator, then to a registered person. Existing notices keep their ids and aren't rerouted.

    #3235Link

  • FixedAfter a reboot or tmux restart, an interrupted rig seat set-runtime switch settles as abandoned, so sends to the seat go through again; it hasn't yet been tried across a real reboot. A community contribution.

    After a host reboot or a tmux server restart, a rig seat set-runtime switch that was still before commit settles as abandoned once its deadline has passed, its staging session is gone and no observed pane shows the staged successor. Sends to the seat then go through again. Any sign of the successor keeps it pending, and the deadline is an estimate, not proof that nothing is in flight. It settles only at daemon start or on rig seat set-runtime <seat> --recover, and it wasn't tried across a real host reboot or tmux server restart.

    #3109 · thanks @cavalcanticampos · reported by @KM199Link

  • FixedA manual rig compact that stops at a prompt now waits and sends /compact once the seat is idle, and --skip-map can compact a seat at Claude Code's "Context limit reached" screen.

    A manual rig compact whose preparation stops at a prompt returns to its bounded wait instead of disarming, and sends /compact once the seat is idle. Nothing is answered for the person, and a typed draft still stops the attempt. rig compact <seat> --state shows the prompt; an expiry while it still shows names preparation_needs_input. A manual compaction also no longer needs a context-usage reading, so rig compact <seat> --skip-map now compacts a seat at Claude Code's "Context limit reached" screen even with no usage reading (checked once, in Claude Code's default mode).

    #3144Link

  • FixedAn attached or adopted Claude seat can now record its conversation's resume token even without a seat-named status-line file.

    An attached or adopted Claude seat can capture its current conversation's resume token from process metadata when no seat-named status-line file exists, and Claude's conversation title no longer has to equal the seat name. A missing bound pane or an ambiguous session leaves the token unknown. Plain external-CLI attachment without a tmux pane stays unverified, and restore still relaunches an adopted seat under a derived session name.

    #3242Link

  • Fixedrig launch <rig> --seats <seat> no longer refuses because another seat is paused or being typed in, and it takes a seat's session name.

    rig launch <rig> --seats <seat> no longer refuses because another seat in the rig is paused or being typed in; the other seats keep their pane, draft, guard mode and binding, and a paused target still refuses. rig launch also takes a seat's session name, including an adopted seat's raw tmux name or its <name>@<rig> form. A name matching several seats isn't launched. The single-seat form returns seat_ambiguous with candidates; under --seats it is listed in ambiguousSeats while other unambiguous selections proceed normally. If every selection is ambiguous, the reply is seat_ambiguous.

    #3184Link

  • FixedThe TUI's daemon-only start now honours the address the daemon is configured to listen on, instead of loopback alone.

    For the default http://127.0.0.1:<port> target, the TUI's daemon-only start (from its crash cart or start-and-return page) passes only the port, so it honours the daemon's configured bind, or its default loopback-plus-Tailscale bind when none is configured, instead of loopback alone. It no longer promises a kernel that isn't listed.

    #3181, #3227Link

Delivery, the queue and status 8

  • ChangedSetting a task aside or closing it with --summary or --evidence-ref now stores them, instead of refusing the whole update.

    An otherwise-admitted state-changing park or close stores its supplied non-blank --summary or --evidence-ref, instead of refusing the whole update with summary_evidence_not_persistable; note-append and re-estimate rules remain unchanged. A blank value isn't stored, and the receipt names any requested field the stored row doesn't carry.

    #3136Link

  • Changedrig ps summary lines now name the daemon they came from. A community contribution.

    rig ps ends each summary line with the daemon it answered from (· daemon <address>); JSON output is unchanged.

    #3107 · thanks @EZotoffLink

  • ChangedA watchdog records the session that registered it, when the request names one. A community contribution.

    A watchdog records the request's session header as its registering session when there is one. That's attribution, not an authenticated identity.

    #3194 · thanks @DeryFerdLink

  • ChangedThe queue's waiting reads reuse prepared statements; results don't change.

    The queue's waiting reads reuse their prepared statements per connection. Results don't change, and this isn't claimed to fix a daemon freeze.

    #3214Link

  • FixedText you type while a conditional Enter's checks are waiting is no longer submitted with OpenRig's text. A community contribution.

    A draft typed while a conditional Enter's own checks wait is no longer submitted with OpenRig's text: the guard refuses with draft_input_changed, sends no key and leaves the input as it is. The input read and the later key write are still separate steps; see Known limits.

    #3176 · thanks @billbenettiLink

  • FixedA send to a busy Codex seat with an empty input is now delivered once instead of being left in the input; its own tests show this, and it isn't yet checked with the real programs.

    A send to a busy Codex seat (seen with 0.167.1 and 0.167.2) whose input is empty is delivered once, instead of being pasted and left in the input, neither delivered nor held. OpenRig now reads Codex's "tab to queue" hint row, and a person's draft under that hint is still held. That's shown by the change's own tests; it wasn't checked with the real programs when this release was tested.

    #3232Link

  • FixedA notice from human@host no longer suggests replying there, because that address names no person.

    A notice from human@host no longer hints at replying there: the hint says that address names no person.

    #3132Link

  • Fixedrig edge add no longer says restore refuses a cycle, and a ceremony episode keeps its name when what counts as coordination changes. A community contribution.

    rig edge add's cycle refusal no longer says restore refuses a cycle, and an open resumed ceremony episode keeps its name when what counts as coordination changes.

    #3163, #3192 · thanks @dajiaohuang, @billbenettiLink

Workflows 2

  • Addedrig workflow list filters by mission, project, rig, workflow, slice or tag. A community contribution.

    rig workflow list filters by mission, project, rig, workflow, slice or tag; repeated tags combine with AND.

    #3170 · thanks @dajiaohuang · reported by @billbenettiLink

  • FixedAfter a queue handoff closes a workflow step, rig workflow route to the same target adopts the handoff's successor instead of writing a new task.

    When a queue handoff closed a workflow's frontier packet, rig workflow route to the same target adopts the queue's single handoff successor, writing nothing to the queue, and rig workflow project records the agent's exit on the closed packet without changing its queue history. A route that can't adopt returns 409. A write-free replay needs the same original --packet; a canceled packet isn't treated as terminal; a lone handed-off graph packet projected as waiting still reports the graph as active; and route doesn't mark a parent workflow recovered.

    #3252, #3255Link

Connected assistants, Codex and tools 10

  • AddedMCP tools for rig ps, rig send, rig capture and the queue can name a registered remote host, from an owner connection. A community contribution.

    MCP tools whose CLI verb takes --host accept a host for a registered http host: rig_ps, rig_send, rig_capture, and the queue create, show, list, update and handoff tools. Only an owner connection can name a remote host; a granted connection is refused, and an ssh host gets a teaching error.

    #3010 · thanks @EZotoffLink

  • Addedrig mcp token rotate <name> gives an MCP grant a fresh token in place; clients must switch at once. A community contribution.

    rig mcp token rotate <name> gives a file-backed MCP grant a fresh token in place. Clients must switch: the old token stops matching at the next authentication, and there's no grace window.

    #3200 · thanks @DeryFerdLink

  • AddedEach Codex seat can have its own filesystem rules (read, write and deny) through codex_permissions; enforcement hasn't yet been checked with a real Codex seat. A community contribution.

    Per-seat Codex filesystem policies: codex_permissions has an opt-in filesystem form with native read, write and deny rules for that seat's own invocation, carried through managed launch, resume, restore and rebuild. A concrete conflict in the seat's effective Codex configuration stops the launch and names a remedy; a configuration that can't be read keeps the authored invocation and reports "policy not verified". The configuration read and the start aren't atomic. Codex enforces the rules. A seat's resume command in rig ps and node detail carries the policy's flags, but not yet its model and effort. When this release was tested, enforcement wasn't checked with a real Codex seat, and neither were a manual resume with that command nor two seats keeping their policies apart.

    #3108, #3239 · thanks @KayhuskLink

  • AddedThe TUI's Projects view can show missions and slices across every registered host, with each host's status. A community contribution.

    The TUI's Projects view can show missions and slices across every registered host, each with a status (ok, stale, unreachable, auth-failed, unsupported or unsupported-transport). A failed read shows that host's last-known rows marked stale; that cache is in memory, so after a daemon restart a failed host shows no rows.

    #3191 · thanks @EZotoffLink

  • Addedrig ps --nodes --json --fields activityState returns each seat's activity, and daemon.seat_poll_interval_ms says a change applies after a daemon restart. A community contribution.

    rig ps --nodes --json --fields activityState returns each seat's activity object, and daemon.seat_poll_interval_ms reports that a change applies after a daemon restart.

    #3240, #3241 · thanks @Kayhusk, @w4rc0nLink

  • Addedscripts/portability-report.mjs --strict exits 1 when the report finds matches. A community contribution.

    scripts/portability-report.mjs --strict exits 1 when the report finds matches; without it nothing changes.

    #3202, #3226 · thanks @DeryFerdLink

  • ChangedThe openrig plugin's README gives GitHub Copilot CLI's install and seat steps.

    The openrig plugin's README gives GitHub Copilot CLI's install and seat steps; Copilot installs the plugin from the repository's main branch, unlike the other hosts' release installs.

    #3224Link

  • ChangedThe rigs skill says how to follow a task handed on to another host, and that rig queue list shows 100 tasks by default.

    The rigs skill says how to follow a task handed on to another host (rig queue show <id> --host <host>), and that rig queue list shows 100 rows by default.

    #3213Link

  • ChangedDocumentation and test fixes. A community contribution.

    Docs and tests: #3197, #3201 and #3203.

    #3197, #3201, #3203 · thanks @DeryFerdLink

  • Fixedrig context get reference/product-journey-sdlc.md resolves. A community contribution.

    rig context get reference/product-journey-sdlc.md resolves.

    #3208 · thanks @KayhuskLink

Behaviour that changed 3

  • ChangedSeats with the built-in standard or open policy now launch with the team default's allowances; before, any recorded policy turned the team default off.

    standard and open seats keep the team default. A seat whose effective policy is the built-in standard or open now launches with the team default's allowances, as a seat with no policy does. Before, any recorded policy turned the team default off.

    #3230Link

  • ChangedSetting a task aside or closing it with --summary or --evidence-ref is now applied instead of refused.

    A state-changing park or close carrying --summary or --evidence-ref is applied instead of refused.

    #3136Link

  • Changedrig ps summary lines end with · daemon <address>. A community contribution.

    rig ps summary lines end with · daemon <address>.

    #3107 · thanks @EZotoffLink

Known limits: 12 for this release. Read them
  • Restore's overall result: a rig can still read fully_restored while a seat restore didn't start (one claimed or added after its roster or snapshot was recorded), or a seat kept in its external CLI attachment, goes unnamed. A seat restore left as a bare shell after "Harness not started" still counts as running in rig ps. restore-check can also say "Restore tries …" for a self-attached member that restore leaves out; that member isn't restored.
  • Draft-aware delivery (#3076): typing after the guard's final check and before the paste can still leave the notice beside the person's draft. In the tested append-mode schedule Enter was refused and nothing was submitted or deleted; this is not a guarantee for every interleaving. Before a conditional Enter, text typed after OpenRig's input read can still be submitted with OpenRig's text; #3176 moved OpenRig's own checks before that read. Neither #3097's nor #3176's narrowing is checked with the real programs on this release.
  • Draft-aware delivery with a wide Claude Code footer: with Claude Code's full-width auto-update-failure footer on screen (seen at 200x50), a seat in the opt-in draft-aware typing mode whose input is empty can hold an ordinary send instead of delivering it. The message is kept, not lost, and rig seat held-messages shows it.
  • Seats at the edit floor can stop for approval, OpenRig's own commands included. A Claude seat running at the harness's edit floor can ask for approval before shell commands, including OpenRig's own read-only rig commands such as rig whoami and rig queue show. A seat with the built-in standard or open policy now keeps the team default; other recorded choices keep their meaning, and the launch plan says whether a seat gets the team default's allowances. A seat that keeps the team default can still ask before the project's own commands, such as running its tests or git add and git commit. Each prompt waits until someone approves it, in the seat or through your own agent, so a team can stall while nobody answers.
  • A question about a seat's prompt can wait with the kernel operator. If you aren't registered as the team's person, OpenRig's question about a seat's prompt doesn't reach you; it waits with the kernel operator. The kernel operator's offer to register you mentions pairing, but seat questions need a registered person too. Registering wasn't tested as a fix for this. This is OpenRig's own question, separate from your agent reading a seat's screen and bringing its prompt to you.
  • Approvals your agent recorded: In one Claude setup, your agent recorded approvals it made itself as "Person approved". Those entries alone do not establish your approval; check the conversation to see who actually decided.
  • A new Claude agent's startup text can stay unsent in its input box while the seat reads ready. Press Enter in its terminal.
  • Managed compaction with Claude Code 2.1.322 (other versions weren't run; 0.7.15 behaves the same):
    • If someone has typed text in a Claude seat's input box when managed compaction runs, OpenRig's /compact can be sent as part of that text instead of as a command. The seat isn't compacted, but rig compact --state reports the compaction, restore and audit as sent. Make sure the input box is empty before compacting, and check that the seat actually compacted.
    • With the draft-aware typing guard turned on, Claude Code 2.1.322 can leave managed compaction's long preparation prompt unsent (it shows as [Pasted text #1]), and the attempt stops as preparation_incomplete.
  • Packaged skills across an upgrade (#3279): a Claude seat that loads the vendored openrig-core plugin reads these skills from the plugin, so it keeps no seat copies to follow. A resumed Codex conversation isn't sent its skill catalog again until a fresh start; the files on disk are current. When an upgrade changes only one file's mode and another file's bytes, and rig down had already removed the first file, the copy is kept and named rather than followed. If saving a skill's new record fails, files whose source changed are named missing, as before, and a later restore tries again.
  • Linked Codex config files: when a Codex seat's config.toml or hooks.json is a symbolic link, OpenRig records its hook trust under the link's target, as in 0.7.14. A change to key it by the file's own name isn't in this release, and such a seat may be asked to review hooks again. With a linked config.toml, OpenRig can also miss a setting stored for it that turns OpenRig's hooks off, and set those hooks up anyway when it moves them into hooks.json. (#3078)
  • Daemon memory: 0.7.14's comparison under load established neither equal memory nor a regression against 0.7.13. This release makes no memory claim.
  • From 0.7.15: its known limits still apply, except where this release changes them: #3232 repairs the input read behind the busy Codex seat case, #3230 changes which seats launch at the edit floor, and #3176 narrows the conditional Enter window described above. 0.7.15's other limits weren't re-checked for this release unless named here.

Thanks 8

Thank you to everyone whose work is in this release: @DeryFerd, @billbenetti, @EZotoff, @Kayhusk, @dajiaohuang, @cavalcanticampos and @w4rc0n.

Thanks also for the reports behind these fixes: @billbenetti (#2985, #2728), @KM199 (#3103) and @Kayhusk (#3193).

OpenRig 0.7.15OpenRig 0.7.15 is a steadiness release. When an OpenRig update changes its own Codex hooks, OpenRig now renews their approval itself, unless you've made your own choice about them, so your Codex agents don't stop at Codex's hook review. A slow daemon start gets three minutes before it's reported pending, a restart now picks up the saved conversation of an agent whose saved startup details are missing instead of stopping, and Slack link previews are off by default. There are fixes across delivery, Slack replies, terminal views and connected agents, many from people using OpenRig.4 added16 changed9 fixed

9 people thanked · Release notes

Highlights

  • AddedWhen an OpenRig update changes its own Codex hooks, OpenRig renews their approval itself, so Codex agents don't stop at Codex's hook review; your own hook choices still get the review. A community contribution.

    OpenRig renews its own changed Codex hook approvals. When a new openrig-core changes one of OpenRig's six Codex hook declarations, the launch that installs it renews those approvals from OpenRig's own record instead of stopping at Codex's hook review. This runs at daemon start in the daemon's Codex home, when hooks are on and a Codex seat selected openrig-core, and at each such seat's launch in its own Codex home. It renews only when the installed plugin matches the shipped one and every current approval matches OpenRig's saved record. A person's own choice in any layer OpenRig reads keeps the review; profile files passed with -p aren't read. No real Codex seat ran in its tests.

    #3143 · thanks @KayhuskLink

  • ChangedA slow daemon start now gets three minutes, not 20 seconds, before it's reported pending, and rig daemon start shows its progress about every 20 seconds.

    A slow start: rig daemon start now gives the daemon child it started a 180-second readiness budget, instead of 20 s, and prints "Waiting for daemon child <PID> readiness (…s elapsed; 180s limit)" about every 20 s. A quick start still returns at once, and a child that exits ends the wait. Let the wait finish. The budget bounds scheduling: synchronous work can run past the budget. A child still not ready when that budget is exhausted is reported pending as before: "Daemon startup is pending after the readiness deadline". Readiness remains unconfirmed; the child keeps running and the startup reservation is retained. Inspect the address and log it prints, and don't start it again until its restart steps are done: stop the named child PID and wait for it to exit, inspect daemon-start.lock, and only when both recorded launcher and child PIDs are absent, archive the lock and run rig daemon start. rig daemon stop cannot stop that unpublished child.

    #3118Link

  • ChangedIn a rig with pods, restore now tries an agent's saved conversation when its saved startup details are missing, instead of stopping.

    For an eligible seat in a rig with pods that restore starts in its own pane, a resume token with no saved startup context now lets restore try the saved conversation with an empty plan. It records the startup_context gap. A successful resume with that gap makes the rig read partially_restored; a missing conversation or failed start keeps its own status. No saved startup plan is replayed or saved startup-context row written; the adapter's ordinary bootstrap and existing skill restoration still run. An external CLI attachment is kept, no-token seats still wait for a decision, and legacy seats are unchanged. restore-check reads an eligible seat with a token yellow; for one with no saved context and no eligible token, it points to the read-only rig up <rig> --existing --plan preview.

    #3177Link

  • ChangedSlack link and media previews on posts to a person are off by default; run rig slack setup --unfurl on to turn them back on. A community contribution.

    Slack previews: posts to a person no longer show link and media previews by default. An existing install stops showing them after its next connector rewire or daemon restart. Run rig slack setup --unfurl on to turn them back on; earlier previews aren't removed.

    #3157 · thanks @dajiaohuangLink

Before you upgrade 4

  • ChangedStop the daemon, back up the database, install 0.7.15, then start the daemon again; your agents keep running through the restart.

    Stop the daemon, back up the database, install 0.7.15, then start the daemon. Your agents keep running through a daemon restart; don't use rig down, which ends them.

    Link

  • ChangedOne database update runs before the daemon listens. Going back to 0.7.14 after it isn't established, so keep the backup. A community contribution.

    One migration runs before the daemon listens. Migration 165 adds four columns and two indexes to activity_grants, binding a runner's activity credentials to its actual launch. Going back to 0.7.14 after it isn't established; keep the backup.

    #3060 · thanks @smotaLink

  • ChangedA slow daemon start now gets three minutes, not 20 seconds, before it's reported pending, and rig daemon start shows its progress about every 20 seconds.

    A slow start: rig daemon start now gives the daemon child it started a 180-second readiness budget, instead of 20 s, and prints "Waiting for daemon child <PID> readiness (…s elapsed; 180s limit)" about every 20 s. A quick start still returns at once, and a child that exits ends the wait. Let the wait finish. The budget bounds scheduling: synchronous work can run past the budget. A child still not ready when that budget is exhausted is reported pending as before: "Daemon startup is pending after the readiness deadline". Readiness remains unconfirmed; the child keeps running and the startup reservation is retained. Inspect the address and log it prints, and don't start it again until its restart steps are done: stop the named child PID and wait for it to exit, inspect daemon-start.lock, and only when both recorded launcher and child PIDs are absent, archive the lock and run rig daemon start. rig daemon stop cannot stop that unpublished child.

    #3118Link

  • ChangedThe openrig plugin carries the CLI's version, 0.7.15, and openrig-core moves to 0.1.30.

    The plugins: the openrig plugin carries the CLI's version, 0.7.15. openrig-core moves to 0.1.30, because its skills changed.

    Link

Also in this release 22

Under load 4

  • AddedThe slow-operation log names more of what a slow queue call or nodes read was doing.

    The slow-operation log adds three queue sites and three selected steps of an ordinary nodes read: nodes.inventory.build, nodes.inventory.activity_sync and nodes.inventory.terminal_work. These nodes records are written after a slow call completes; a missing record does not rule out unfinished work or work outside those steps. This changes no behaviour.

    #3100, #3138Link

  • ChangedWhen OpenRig retries a wake, it looks for refused prompts among open tasks instead of scanning the whole history on every tick.

    The wake ladder reads its prompt-refusal candidates from the open rows, instead of scanning the whole transition log on every tick. It returns the same rows. This removes one repeated scan; it isn't a measured fix for every stall.

    #3098Link

  • ChangedThe execution view reads the queue in steps and lets other work run between them, so a mission filter that matches few tasks no longer holds up the daemon.

    The execution view's candidate read steps through the queue in windows and, on its cooperative path, yields to the event loop between them, so a mission filter that matches few rows no longer holds the loop for a whole history walk. One large row, or the history count, can still take time. Inside a transaction, on a memory or temporary database, or on a non-WAL file, the candidate read keeps its synchronous fallback.

    #3122Link

  • ChangedSnapshot refreshes share process listings between seats where they can. A community contribution.

    Snapshot refreshes share process listings where each seat's order and the 2 s freshness allow; each seat still gets its two ordered observations and its own fallback. The reduction is derived from the source, not measured.

    #3154 · thanks @dajiaohuangLink

Restore and seats 3

  • Addedrestore-check and a full restore warn when a snapshot's named Codex profile has since been cleared from the seat; restore uses the current one. A community contribution.

    restore-check and a full restore warn when a snapshot recorded a named Codex profile that the current seat has cleared; restore uses the current selection. Nothing is refused.

    #3155 · thanks @dajiaohuangLink

  • ChangedWhen rig seat restart --keep-conversation can't restart a seat whose tmux session is gone, it gives you the rig launch command that brings it back. A community contribution.

    When rig seat restart --keep-conversation refuses a recoverable seat whose tmux session is gone, it names the way back: rig launch '<rig>' '<node>' (add --plan to preview).

    #3135 · thanks @KayhuskLink

  • FixedA context-usage watchdog watches its seat's current agent, not an earlier one, and skips a tick it can't place instead of stopping.

    A context-usage watchdog reads its own seat's current occupant, not an archived generation's. A context watch whose seat can't be pinned, or has no recorded tenure, skips that tick with its reason instead of ending.

    #3027, #3139Link

Delivery and people 4

  • AddedSlack link previews on posts to a person are now a setting, rig slack setup --unfurl on|off, and they're off by default. A community contribution.

    Slack previews on posts to a person are a setting: rig slack setup --unfurl on|off, and rig slack status shows which is in effect from the connector's next rewire. The default is off; see "Behaviour that changed".

    #3157 · thanks @dajiaohuangLink

  • ChangedIn a seat with the draft-aware guard, OpenRig checks again for typing just before an automatic paste and holds the message if someone's active, as its own tests show; it isn't yet checked with the real programs. A community contribution.

    Right before an automatic paste into a seat with the draft-aware guard, OpenRig re-checks: it holds the paste after recent client activity, re-reads the input after a short wait, and holds when tmux can't be read. The message is held and retained; rig seat held-messages shows it. An ordinary guarded paste waits about 300 ms longer. This narrows #3076's window; it doesn't close it. This is shown by the change's own tests; it's not yet checked with the real programs on this release.

    #3097 · thanks @billbenettiLink

  • FixedA terminal seat whose tmux session has a different name now gets a send's exact text, and a queued wake no longer types OpenRig's From/To lines into its shell. A community contribution.

    A terminal seat whose tmux session runs under another name gets the exact text of a send, and a queued wake no longer types OpenRig's From/To envelope into its shell.

    #3074 · thanks @Nikhila-Dhevi-RLink

  • FixedA Slack answer to a reply in an older thread now posts back into that thread instead of as a new message. A community contribution.

    When the arrival note is recorded before the answer is routed, an answer to a reply in an older Slack thread posts back into that thread, not as a new top-level message; see Known limits for when it posts top-level. Only the conversation's newest thread answers a parked question, as before.

    #3120 · thanks @zichen0116Link

Connected assistants 4

  • ChangedAn agent that asks rig_team for its team by display name is told to leave rigId out, and a hosted member with no wake trigger is told when it picks up work.

    An assistant that passes its team's display name as rig_team's rigId is told to leave rigId out to see its own team, and a hosted member with no wake trigger is told it picks up work when its person asks, or on a schedule they set.

    #3104Link

  • ChangedAn external grant that works its own inbox is told only about the tools it's offered.

    An external grant that works its own inbox is told only about the tools it's offered.

    #3140Link

  • ChangedThe openrig plugin needs Claude Code 2.1.119 or later; on earlier versions, with its seat setting left blank, the skill loads but the agent has no OpenRig tools.

    The openrig plugin needs Claude Code 2.1.119 or later. On earlier versions, with the plugin's OpenRig seat setting left blank, Claude Code drops its MCP server: the skill loads, but the agent has no OpenRig tools.

    #3137Link

  • FixedThe TUI keeps connected agents' check-in lines when a rig's seat list can't be read, and shows the error beside them.

    The TUI keeps connected assistants' check-in lines when a rig's seat inventory can't be read, with the error beside them.

    #3105Link

Codex, runners and harnesses 6

  • ChangedRunner activity reports are tied to the launch OpenRig started, and a replacement's start revokes the old one's access. A community contribution.

    Runner activity grants are bound to the actual launch, and the replacement's activation revokes its predecessor's grant. A grant made before this release stays tied to the seat's occupant until then. A grant that can't be bound never blocks a launch or restore. This attributes reports to the run OpenRig selected; it doesn't prove a runner's identity.

    #3060 · thanks @smotaLink

  • FixedA Codex seat's resume command in the node inventory and detail panel now matches what a real resume runs, with a label when the launch differed. A community contribution.

    A Codex seat's resume command in the node inventory and detail panel is built from what a real resume uses, with a label when the recorded launch differs. Workspace options that aren't recorded per launch can still read as a match.

    #3043 · thanks @AummadourLink

  • FixedTerminal tiles find tmux again when its saved path is gone, instead of exiting until a daemon restart. A community contribution.

    Terminal views find tmux again when its cached path is gone, instead of tiles exiting 126 until a daemon restart.

    #3129 · thanks @vanducngLink

  • FixedA SKILL.md with Windows (CRLF) line endings is now found and reaches the seat's managed plugins. A community contribution.

    A SKILL.md with CRLF line endings is discovered and reaches a seat's managed plugin loadout.

    #3153 · thanks @dajiaohuangLink

  • Fixedrig context work-install --mission warns when the mission doesn't exist.

    rig context work-install --mission <missing> warns that the mission doesn't exist, and missionRoot reads null; the exit code is unchanged.

    #3141Link

  • FixedOpenRig's own transitions no longer count toward ceremony amplification, and the post-restore audit message matches the restore skill. A community contribution.

    OpenRig's own transitions (daemon@kernel and system:*) no longer count toward ceremony amplification, and the post-restore audit message matches the restore skill.

    #3124, #3127 · thanks @billbenettiLink

Behaviour that changed 1

  • ChangedRestoring an agent with a resume token but no startup context now tries its saved conversation, and reads partially_restored when it works, instead of stopping as not restorable.

    Restore of an eligible seat with a resume token and no startup context now tries its saved conversation, and a successful resume reads partially_restored. It used to stop with "Harness not started: no startup context" and read the rig not restorable.

    #3177Link

Known limits: 12 for this release. Read them
  • Daemon start: the longer readiness budget doesn't identify or cure the cause of a slow start, synchronous work can run past the budget, and a child still not ready when that budget is exhausted stays pending. (#3118)
  • Daemon memory: 0.7.14's comparison under load established neither equal memory nor a regression against 0.7.13. This release makes no memory claim.
  • Restore's overall result: a rig can still read fully_restored while a seat restore didn't start (one claimed or added after its roster or snapshot was recorded), or a seat kept in its external CLI attachment, goes unnamed. A seat restore left as a bare shell after "Harness not started" still counts as running in rig ps. restore-check can also say "Restore tries …" for a self-attached member that restore leaves out; that member isn't restored.
  • Draft-aware delivery (#3076): typing after the guard's final check and before the paste can still leave the notice beside the person's draft. In the tested append-mode schedule Enter was refused and nothing was submitted or deleted; this is not a guarantee for every interleaving. The prior conditional-send Enter-window case is unchanged: characters typed during OpenRig's last checks before Enter submitted with OpenRig's text.
  • Draft-aware delivery with a wide Claude Code footer: with Claude Code's full-width auto-update-failure footer on screen (seen at 200x50), a seat in the opt-in draft-aware typing mode whose input is empty can hold an ordinary send instead of delivering it. The message is kept, not lost, and rig seat held-messages shows it. On 0.7.14, the clipped footer at 80x24 didn't do this.
  • Draft-aware delivery to a busy Codex seat: on Codex (seen with 0.167.1 and 0.167.2), a send to a seat in the opt-in draft-aware typing mode while it's busy can be pasted into its input without Enter. The message isn't delivered, and it isn't kept for rig seat held-messages. A deliberate send reports failed, and its text stays in the seat's input box. This was seen on 0.7.12 and 0.7.14, and there's no fix for it in this release.
  • Seats at the edit floor can stop for approval, OpenRig's own commands included. A Claude seat running at the harness's edit floor can ask for approval before shell commands, including OpenRig's own read-only rig commands such as rig whoami and rig queue show. Choosing a built-in policy such as standard when your team is set up doesn't change that at launch: the plan shows launch_posture=floor. Each prompt waits until someone approves it, in the seat or through your own agent, so a team can stall while nobody answers.
  • Approvals your agent recorded: In one Claude setup, your agent recorded approvals it made itself as "Person approved". Those entries alone do not establish your approval; check the conversation to see who actually decided.
  • A new Claude agent's startup text can stay unsent in its input box while the seat reads ready. Press Enter in its terminal.
  • Linked Codex config files: when a Codex seat's config.toml or hooks.json is a symbolic link, OpenRig records its hook trust under the link's target, as in 0.7.14. A change to key it by the file's own name isn't in this release, and such a seat may be asked to review hooks again. With a linked config.toml, OpenRig can also miss a setting stored for it that turns OpenRig's hooks off, and set those hooks up anyway when it moves them into hooks.json. (#3078)
  • Slack reply threads: recording the arrival note is best effort: a failed write is not retried and that answer posts top-level. Creating the message and recording the arrival note are separate writes, so a notification can also be posted before the note is recorded, with the same top-level outcome. The person's message is kept. (#3120)
  • From 0.7.14: its known limits still apply, except where this release changes them. #3105 fixes the TUI tables' dropped check-in line, and #3097 narrows the draft-aware paste window described above, as its own tests show. 0.7.14's other limits weren't re-checked for this release unless named here.

Thanks 9

Thank you to everyone whose work is in this release: @dajiaohuang, @Kayhusk, @billbenetti, @Aummadour, @smota, @vanducng, @zichen0116 and @Nikhila-Dhevi-R.

Thanks also for the reports behind these fixes: @Aummadour (#2989), @vanducng (#3128), @Alejandro-SJ (#2990), @billbenetti (#2976) and @Kayhusk (#3131).

OpenRig 0.7.14A polish release with a smoother first setup: before your first team starts, OpenRig's operator agent now checks that you're signed in to each coding agent the team uses, and if one isn't, it tells you before launch and lets you sign in or adapt the team.8 added11 changed13 fixed

10 people thanked · Release notes

What you can do now

Your own subscriptionsImproved

Before your first team starts, setup and rig doctor say which logins it needs, and the operator lets you choose if one is missing.

Details

The queueImproved

rig queue list filters exactly by --tag, --mission and --slice, and several tags must all match. Thanks to @Aummadour.

Details

Terminal tilesImproved

rig terminal open --provider herdr reuses a live Herdr workspace, and Rex tiles show each agent and what it's doing. Thanks to @Kayhusk and @Tankard.

Details

Before you upgrade 4

  • ChangedStop the daemon, back up the database, install 0.7.14, then start the daemon again; your agents keep running through the restart.

    Stop the daemon, back up the database, install 0.7.14, then start the daemon. Your agents keep running through a daemon restart; don't use rig down, which ends them.

    Link

  • ChangedThree database updates run before the daemon listens, and one can take a while on a large database. Going back to 0.7.13 after them isn't established, so keep the backup.

    Three migrations run before the daemon listens. Migration 163 adds the network_installations table and four columns to network_bindings. Migrations 164 and 166 build indexes. The author's measurement of 166 took 3.47 s on 28,976 rows, not a real installation's size, so a large database can take longer. The write overhead, and going back to 0.7.13 after these three migrations, aren't established; keep the backup.

    #3007, #3008, #3090Link

  • ChangedIf the start is reported pending, don't start the daemon again until you've followed the restart steps the message prints; rig daemon stop can't stop that child.

    If the start is reported pending: the CLI waits 20 s, then may print "Daemon startup is pending after the readiness deadline". Readiness remains unconfirmed. It leaves the child running and the startup reservation retained, without recording the daemon. Inspect the address and log it prints. The child may later answer, and status can then report it running, but that does not finish this start's recording or release its reservation. Don't start it again until the steps below are done. The message's restart steps stop that child and clear the reservation: stop the named child PID and wait for it to exit, inspect daemon-start.lock, and only when both recorded launcher and child PIDs are absent, archive the lock and run rig daemon start. On a large database the new start can be reported pending again; reaching a recorded start this way hasn't been tested. rig daemon stop cannot stop that unpublished child.

    Link

  • ChangedThe openrig plugin now carries the CLI's version, 0.7.14; openrig-core stays 0.1.29.

    The openrig plugin carries the CLI's version, 0.7.14; openrig-core stays 0.1.29.

    Link

Also in this release 25

Under load 5

  • ChangedNode reads from rig ps --nodes, the TUI and busy agents now take turns, one step at a time, instead of arriving as one burst.

    Node reads (rig ps --nodes, the TUI, several agents at once) take turns, one step at a time. In the change's own tests, health checks and queue reads were no longer held behind a whole burst. A comparison under load didn't attribute a gain to this change: health checks and queue reads were faster for the release as a whole, rig ps --nodes showed no change, and sends were inconclusive.

    #3101Link

  • ChangedQueue listings over a long history use indexes instead of scanning all of it.

    Bounded queue listings over retained history use indexes for their ordering and for live and archived owner notifications.

    #3090Link

  • ChangedCodex agents checked in the same readiness poll share process listings instead of each reading their own. A community contribution.

    Codex seats re-checked in one readiness poll share process listings where each seat's observation order and the 2 s freshness allow; each keeps its own later observation and its own fallback.

    #3061 · thanks @KayhuskLink

  • ChangedNew tmux servers raise their open-file limit, so many panes and viewers are less likely to run out.

    New tmux servers raise their soft open-file limit to 8,192 or the hard limit where they can, keeping an already higher limit. This makes descriptor exhaustion less likely as panes and viewers add up; servers already running keep their limits.

    #3070Link

  • FixedAn agent that hands work to other agents gets one ongoing reminder per agent about its unclaimed work, not one per task. A community contribution.

    A delegation parent gets one standing notice per child seat for unclaimed rows, not one per row, and held work gets its notice back when its typing hold clears.

    #3049, #3082 · thanks @billbenettiLink

Your team and the people it works for 6

  • AddedAn agent connected through a grant service (experimental) reaches a seat by the name your team shows, and a wrong or ambiguous name says so.

    An assistant connected over MCP reaches a seat by its plain name, stored under the seat's actual session; an unknown name, or one several seats match, says so.

    This is for hosted agents connected through a grant service (experimental); seats OpenRig launches behave as before.

    #3088Link

  • AddedHosted members (experimental) now appear, with their check-in, in rig ps, rig_team and the TUI.

    Connected assistants appear, with their check-in, in rig ps, rig_team and the TUI's tables, and their person sees plain tool titles.

    #3057, #3058, #3092Link

  • AddedA team your agent hands work to knows how to ask you a question, and your answer wakes it.

    A team your agent hands work to knows how to ask you a question, and your answer wakes it. A click on an ask with several questions records that choice; the ask stays open until the last one.

    #3059, #3045Link

  • AddedThe skill-only openrig plugin for Claude's plugin directory follows handed-on work and keeps its reply route.

    A skill-only edition of the openrig plugin, for Claude's plugin directory, follows handed-on work and keeps its reply route.

    #3056, #3075Link

  • ChangedWhen nobody is registered, setup and the operator offer to register you as the team's person, and only your yes registers you.

    When the readable person registry holds nobody, rig daemon start and rig gateway participants tell the setup agent to offer registration. The kernel operator is taught to include that offer in its greeting and register only on your yes.

    #3041, #3071Link

  • FixedA pairing request's description of itself is now quoted wherever it's shown.

    A pairing request's description of itself is quoted wherever it's shown.

    #3067Link

Fixes 10

  • FixedAn ordinary send no longer types into an open /model picker in Claude Code or Codex: it's refused until you close the picker, though this hasn't been checked with the real programs yet.

    An ordinary send is refused as needing input while an open Claude Code or Codex /model picker is positively identified; nothing is typed. Close the picker before trying to deliver the message. This is shown by the change's own tests; it hasn't yet been checked with the real Claude Code and Codex programs on this release.

    #3083Link

  • FixedResuming a Codex agent's conversation, including with rig up --existing, no longer adds OpenRig's guidance to your tracked AGENTS.md on Codex 0.164.0 or later in a rig with pods.

    On a resume of a Codex seat's own conversation in a rig with pods, including rig up --existing, OpenRig avoids adding missing guidance blocks to the repository's tracked AGENTS.md when Codex is 0.164.0 or later, no guidance file or developer instructions are configured, and the configuration and block sources can be read.

    #3039Link

  • FixedWith automatic prompt answering on, Claude Code's gated-grants trust check is never answered for you. A community contribution.

    With recovery.auto_drive_provider_prompts on, Claude Code's gated-grants trust check is never answered for you, and the plain trust prompt is answered "Yes".

    #3073 · thanks @billbenettiLink

  • Fixedrig broadcast now shows a held recipient as retained, not sent.

    rig broadcast prints a held recipient as retained, not sent.

    #3054Link

  • FixedErasing an account also removes OpenRig's own wakes and notices for its agents.

    Account erasure also removes OpenRig's own wakes and notices for that account's seats.

    #3089Link

  • FixedA snapshot without sessions reports a clear blocker instead of crashing, and a retried import recovers the original rig. A community contribution.

    A snapshot without sessions returns its invalid_snapshot_data blocker instead of throwing a TypeError; the restore still stops there. A retried no-launch import recovers the original rig by its operation ID.

    #3069, #3042 · thanks @cavalcanticampos, @KayhuskLink

  • FixedA rebuilt agent's briefing lists only the newest three older recaps by default. A community contribution.

    A rebuilt briefing limits optional superseded recap paths to the newest three by default when one folder covers that history; the current recap and all artifact records remain. Other layouts keep the full list, and output.rebuild_recaps set to 0 lists all paths.

    #3055 · thanks @KayhuskLink

  • Fixedrig compact --state names the input check that stopped a managed compaction, and the TUI graph shows an unknown agent as unknown.

    rig compact --state names the input check that stopped a managed compaction, and the TUI's graph shows a seat the daemon reads as unknown as unknown.

    #3053, #3046Link

  • FixedSetting a context-pressure threshold explains an environment override that flips it, and rig workflow validate warns that harness pins aren't checked. A community contribution.

    Setting a context-pressure threshold explains when an environment override inverts the pair, and rig workflow validate warns that harness pins aren't checked against seats.

    #2567, #3102 · thanks @Totopo27, @cavalcanticamposLink

  • FixedThe config browser now shows each setting's type, choices, range and format. A community contribution.

    The config browser's entries say each setting's type, choices, range, format and write route.

    #3050 · thanks @w4rc0nLink

Experimental 2

  • Addedrig network is experimental and unsupported, and its connector runs even with nothing bound.

    rig network is experimental, unsupported and at your own risk. Its connector isn't inert: the daemon starts it, sweeps leftover credential folders and schedules local rounds even with no binding.

    #3007, #3084Link

  • AddedA grant service can hold back only new work under its fair-use limit, and an app can read what needs a person by link. Experimental.

    A grant service can hold back only new work under its fair-use limit, and an app can read what needs a person, and the answers to it, by link.

    #3048, #3008Link

Behaviour that changed 2

  • ChangedNode responses are no longer one snapshot, and in a burst each comes a little later: about 43 ms against 21 ms median.

    Node reads: a nodes response is no longer one snapshot across its steps, and in a burst each nodes response comes later: about 43 ms against 21 ms median in a 24-request burst. One very large rig is still one step.

    #3101Link

  • ChangedAn agent connected through a grant service now gets one of three clear errors when the name doesn't resolve: ambiguous, not found or unchecked.

    An assistant naming a seat now hears three errors: destination_ambiguous (several seats match; the candidates are listed), destination_not_found (no seat it can reach has that name) and destination_unchecked (the team couldn't be read; try again).

    #3088Link

Known limits: 7 for this release. Read them
  • Queue listings: the new indexes aren't a cure for every stall. Listings of active work showed no gain, one case was slower, and writes weren't measured. (#3090)
  • Daemon memory: in a before-and-after comparison under load, the daemon's resident anonymous memory and its memory when idle afterwards had medians about 23-25 MiB higher on 0.7.14 than on 0.7.13, but the two versions' runs overlapped. Neither equal memory nor a regression is established.
  • Draft-aware delivery (#3076): an automatic OpenRig notice can still be left beside a draft started during delivery. In the reproduced paste-window cases the person's draft stayed intact and no Enter was sent, but OpenRig's text stayed in the input. Those cases don't cover a later window. On a conditional send, one that names the conversation it expects, an isolated test with a scripted terminal showed characters typed while OpenRig ran its last checks before Enter submitted together with OpenRig's text, and the send reported success. The same test reproduces it on 0.7.13. It hasn't been tested with a real client or model.
  • The TUI's tables can drop a connected assistant's check-in line when its rig's seat inventory can't be read; rig roster still prints it. (#3105 isn't in this release)
  • Repository guidance on restore: rigs without pods, old or unknown Codex versions, configured guidance and unreadable configuration keep the existing file path. Fresh, fork and handover launches are outside this resume fix. Existing managed blocks may still refresh, and the seat-skills line still belongs to the file writer; check git status. A block whose source can't be read is reported missing.
  • Linked Codex config files: when a Codex seat's config.toml or hooks.json is a symbolic link, OpenRig records its hook trust under the link's target, as in 0.7.13. A change to key it by the file's own name isn't in this release, and such a seat may be asked to review hooks again. With a linked config.toml, OpenRig can also miss a setting stored for it that turns OpenRig's hooks off, and set those hooks up anyway when it moves them into hooks.json. (#3078)
  • From 0.7.13: its known limits still apply, except where this release fixes them. The runtime fixes cover adding missing guidance on the eligible Codex resumes described above (#3039) and the unquoted pairing description (#3067). The fix for recognized model pickers (#3083) is shown by the change's own tests and hasn't yet been checked with the real programs on this release. This release also changes the operator-first registration (#3041, #3071) and pre-launch login guidance (#3077). In a few test runs with real agents, the operator offered registration once in its greeting, on Claude Code and on Codex (one run each); a no registered nobody, and a yes registered the default person. The person saw the offer in 3 of 4 runs; in the fourth, the setup agent didn't pass the operator's offer on. The login guidance worked in both runs tested, once from the setup agent and once from the operator. 0.7.13's other limits weren't re-checked for this release unless named here.

Thanks 10

Thank you to everyone whose work is in this release: @Kayhusk, @billbenetti, @cavalcanticampos, @Aummadour, @Tankard, @w4rc0n and @Totopo27.

Thanks also for the reports behind these fixes: @Kayhusk (#3035), @Tankard (#2583), @dajiaohuang (#2529), @billbenetti (#2728), @emilio-gagliardi (#3087), @korallis (#161) and @w4rc0n (#3017).

OpenRig 0.7.13When you answer a permission request, you now get a note back saying who decides it, and the waiting agent gets the decision in about half a second. A Claude agent that hits its usage limit now waits for the stated reset instead of being retried.6 added9 changed8 fixed

14 people thanked · Release notes

What you can do now

Permission requestsImproved

When a runner agent asks permission, your answer now gets a note back: who decides it, and whether the tool ran. The waiting agent has the decision in about half a second. If what you typed isn't clear, the agent reading it asks you back in your Feed, and your reply decides. Closing a request without deciding permits nothing.

DetailsAlso: how the agent reads your answer

Usage limitsImproved

A Claude agent that hits its usage limit now waits for the reset time in Claude's message, for example "resets Nov 10, 4pm", and picks its work back up then. Before, it was retried every few minutes. Thanks to @cavalcanticampos, and to @alperta for the report.

Details

Permission postures for a first teamImproved

Before your first team starts, the operator tells you which commands it will ask about. It then makes one offer: allow the command families your goal repeats, for this project only. Say no and the team's defaults stay, and the offer isn't repeated.

Details

Being reachable

Setting up OpenRig now offers to register you as the team's person, so your agents' questions have somewhere to go. rig daemon start and the rigs skill both make the offer. Nothing is registered without your yes, and rig gateway human add registers you any time.

Details

Guidance filesImproved

OpenRig now keeps your edits to its blocks in AGENTS.md and CLAUDE.md, and removes duplicate copies it recognizes. You can tune its guidance for your project without the next update undoing it.

Details

Before you upgrade 2

  • ChangedBack up your database, install 0.7.13 the way you installed OpenRig, then restart the daemon; your agents keep running. Three database updates run on its first start, and going back to 0.7.12 after them isn't established.

    Back up the database, install 0.7.13, then restart the daemon: rig daemon stop, copy the database file (rig config get db.path prints its path), install OpenRig 0.7.13 using your existing installation method, then rig daemon start. Your agents keep running through a daemon restart; don't use rig down, which ends them. Three migrations run on the daemon's first start: 160 and 161 (for the experimental hub connector below) and 162 (indexes for session reads). Going back to 0.7.12 after them isn't established.

    #2993, #2997Link

  • Changedopenrig-core moves to 0.1.29, and the openrig plugin now shares the CLI's version number. If a Codex agent asks for hook approval after the upgrade, approve the hooks to continue.

    openrig-core is 0.1.29, and the openrig plugin now carries the CLI's version, 0.7.13. A Codex seat can ask for hook approval after the upgrade; see Codex hook review after an upgrade below.

    #3034, #3064Link

Also in this release 15

Answering your team 1

  • AddedA hosted member's roster entry shows whether it's checking in: checking in, overdue, no check-in yet, on request or unknown. Experimental and off by default.

    A connected assistant (a hosted member; experimental and off by default) shows whether it's checking in, against a cadence its roster entry states (check_in_minutes, or check_in_on_request: true): checking in, overdue, no check-in yet, on request, or unknown. rig roster show and find print it as a Check-in line. It's a status only: work for a member that isn't checking in still queues and rings as before.

    #3023Link

Seats, handover and recovery 3

  • FixedA handover whose new agent started but wasn't ready now says it may be running instead of telling you to retry, and it cleans up the old agent's claims and jobs. A community contribution.

    A handover whose successor was launched but not ready says it may be running, instead of "retry": look at the pane first. A handover also cleans up the retiring occupant's own claims and jobs.

    #3003, #3024 · thanks @billbenettiLink

  • FixedAfter rig unclaim, the guidance tells you to end the adopted session's process and tmux session, and a fresh launch reopens the tmux server when it needs to.

    After rig unclaim, the guidance for an adopted session says to end its process and its tmux session, and rig seat stop's help matches. A fresh launch after rig unclaim ended the server's last session reopens the server.

    #2996, #3006, #3014, #3009Link

  • FixedA handover into the seat's own tmux session can take over a claim left by an agent that was removed or archived, and an agent that can't be woken reports to whoever created the task. A community contribution.

    A handover whose successor was launched into the seat's own tmux session can reclaim a claim left by a removed owner, or by an archived owner whose latest session for that node is superseded, detached or exited; a live owner still refuses. When a seat with no declared route can't be woken, the finding goes to the item's creator, skipping a creator that is a terminal seat.

    #2869, #2987, #2995 · thanks @KayhuskLink

Fixes 6

  • ChangedThe daemon stays responsive while it reads a large project's proof.

    Speed: the daemon is much more responsive while it reads a project's proof, which now yields between missions; current-session reads for the node inventory use an index; the daemon's recorder and Linux clipboard discovery no longer wait on the main thread.

    #2970, #2997, #3019Link

  • ChangedThe docs now explain what rig seat clear-attention checks, how compaction notices are routed, and how to start one stopped kernel seat with rig launch. A community contribution.

    Docs: what rig seat clear-attention's check proves, how managed compaction notices are routed, when the keyboard moves in herdr-app, a complete periodic-reminder registration, and starting one stopped kernel seat with rig launch.

    #2964, #2984, #2991, #3002, #3031 · thanks @ziadeh, @dajiaohuang · reported by @todd-dhangoLink

  • FixedClaude's auto-update failure footer no longer holds a send, and a one-time wake that failed without typing anything is retried. A community contribution.

    Delivery: Claude's auto-update failure footers, including one clipped form, no longer hold a send to an idle Claude seat; an unrecognised wake result reads unknown, not delivered; an ordinary one-time park wake is kept and retried while its park is current and the failed attempt typed nothing into the seat (an attempt whose effect is unknown needs checking, and repeating waits and usage-limit expiry keep their own lifecycle); a custody-verified: note whose target is followed by a period, comma or other closing punctuation now verifies it; the Pi runner pane keeps the operator's draft out of the stream.

    #2948, #3016, #3011, #3038, #3004, #2842 · thanks @EZotoff · reported by @CaptObviousLink

  • FixedCompleted Codex 0.167 turns read idle, and a usage-limit banner with a curly apostrophe is detected. A community contribution.

    Codex and Claude: completed Codex 0.167 turns read idle, and unsupported versions stay unknown; a usage-limit banner with a curly apostrophe is detected; refocus bounds Codex context and records what it left out; an unreadable Claude status-line cache gets its own reason.

    #2954, #2879, #2951, #2880 · thanks @Kayhusk, @Coder8124 · reported by @jamesloosliLink

  • FixedThe TUI groups instances by rig and shows a quiet agent as unknown, not idle, and Feed times use your time zone. A community contribution.

    TUI and CLI: instance rows are grouped by rig; for a quiet seat the daemon explicitly reads as unknown, the list, explorer and agent-detail status rows show unknown, not idle (screen motion still shows active, a daemon that serves no activity keeps the screen fallback, and the topology graph is unchanged); Feed times use the configured time zone; the CLI doesn't call a daemon stopped when the shell can't see its process (a sandbox), and says not to start another; ssh options are separated from the target, and the generated attach command quotes the session name.

    #2857, #3012, #3022, #2913, #2973, #2971 · thanks @hgreene624, @Kayhusk, @DeryFerdLink

  • FixedSlice and proof reads stay within their mission, and workflow spec reads survive a restart. A community contribution.

    Scope and workflows: qualified slice reads and proof discovery are scoped by mission; workflow spec reads are recorded across restarts; the spec library skips synthetic alias entries.

    #2960, #2986, #2999 · thanks @Aummadour · reported by @ziadehLink

Experimental 1

  • Addedrig network connects one local seat to a hub you already have. Experimental and unsupported.

    rig network connects one local seat to a hub you already have. Experimental, unsupported and at your own risk. The connector uses the MCP SDK, which the installed package already included in 0.7.12.

    #2993Link

Behaviour that changed 4

  • ChangedYour answer to a runner's permission request is now confirmed with a note; through 0.7.12 none came back.

    A runner's answer is confirmed to you. Through 0.7.12 no note came back, and the runner waited for its next read.

    #3001Link

  • ChangedA usage-limited Claude agent waits for its stated reset, so don't release it on a timer, and look at the pane before retrying a failed handover. A community contribution.

    A usage-limited Claude seat waits for its stated reset; don't release it by hand on a timer. A failed handover may have left its successor running; look at the pane before retrying.

    #2917, #3003 · thanks @cavalcanticampos, @billbenetti · reported by @alpertaLink

  • ChangedRoutine host listings no longer probe SSH hosts, so they can't trip OpenSSH's login blocking; hosts read unknown until rig host doctor checks them. A community contribution.

    Passive SSH host status reads unknown. Routine host listings no longer open a TCP connection to SSH hosts, because repeated probes closed without a handshake can make OpenSSH block real logins for a while. Hosts that used to read reachable now read unknown; rig host doctor still checks actively.

    #2979 · thanks @AummadourLink

  • Changedrig package install leaves a guidance file with a damaged OpenRig block alone and lists it, instead of adding a second copy.

    rig package install leaves a guidance file alone when a recognized managed block has no complete marker pair, lists it under "Left as it is:" and installs the rest, instead of appending a second copy. Launch and restore name such a file (guidance_block_markers_damaged).

    #3020Link

Known limits: 23 for this release. Read them
  • Not in this release: a Codex snapshot restore or rig up --existing can write OpenRig's managed guidance into a tracked AGENTS.md, leaving the worktree modified; check git status after either operation.
  • Not in this release: a person who talks to the kernel operator first, with no other agent setting OpenRig up, isn't offered registration. rig up, rig start and rig context start the daemon without printing the offer either. Register with rig gateway human add. While nobody is registered, a later rig daemon start offers again, even after a no; nothing is registered without your yes. (#3028, #3041 isn't in this release)
  • The hub connector isn't inert: the daemon starts it, sweeps leftover credential folders and schedules local rounds even with no binding; only the pass to a hub is absent. Its migrations apply on upgrade. (#2993)
  • The recorder: a queued begin record can be lost before the durable append, and a stalled worker has no acknowledgement timeout. (#3019)
  • Speed and memory: On one performance host, whole rig queue create invocations had a median about 10.4% slower than 0.7.12 (about +29 ms). Send latency stayed within the comparison's unchanged range. The cause remains unidentified. The standard idle-memory comparison was inconclusive. A post-hoc analysis of the same six runs found 7.9–8.6 MiB (4.2–5.3%) higher daemon RSS across three matched idle windows, using the median of three arm medians per version. The cause and steady-state behavior remain unestablished.
  • Draft-aware delivery (#3076): an automatic OpenRig notice can be left beside a draft started during delivery. This also concerns notices admitted by openrig-urgent and urgent-only modes. In the reproduced 0.7.12 Claude Code and Codex cases, the person's draft remained intact and no Enter was sent, but OpenRig's text stayed in the input. The guard and paste path are unchanged in this cut; a native 0.7.13 reproduction has not run.
  • Native model pickers: with a /model picker open, an ordinary send can act on the picker instead of delivering the message. In 0.7.12 tests it confirmed Claude Code's already-selected default and advanced Codex's model selection; neither message reached the model. Close or deliberately resolve the picker before ordinary delivery. The native 0.7.13 case has not run.
  • Codex hook review after an upgrade: in one test whose Codex home already held earlier hook approvals, rig up --existing stopped for hook review in each Codex pane; approving the hooks resumed all three conversations. A separate test of the same upgrade on a fresh Codex home, on another host, restored without review. The cause of the difference is not established.
  • A first team with Codex installed but signed out: a Claude user's starter team includes a Codex reviewer that waits for a Codex sign-in, and you aren't told beforehand. If Codex is installed, tell the person about the possible sign-in wait before the team starts; signing in first was not tested as a remedy.
  • A first team's permission asks: a command joined with &&, ; or a pipe still asks unless every part is allowed, and OpenRig's own lifecycle commands still ask on Claude seats. (#3029)
  • Usage-limit parking was tested with the limit message from claude -p. If an interactive seat's limit report doesn't carry the message, the seat is retried as before. A reset in the past or more than 8 days away is ignored. (#2917)
  • Handover: two other failures can still say "retry" while a successor may be running: a context delivery failure, and a Codex launch failure after an update prompt wasn't dismissed. Look at the pane first. (#3003)
  • Answers: when a receiving agent asks you back, it can stop at Claude Code's own permission prompt, which you don't see. A receiving agent you choose can still decline to act on a clear answer. A pairing requester's description of itself is quoted for the receiving agent, but still shown unquoted in the request's summary and the notices about it. The TUI's one-line notice after you answer can clear within a frame. (#3030, #3001)
  • Proof reads still pause briefly, and a whole read takes slightly longer. Yielding isn't a hard bound on latency or a single atomic snapshot of the proof. (#2970)
  • rig down keeps no stored host or boot identity, doesn't guard against another program running as you, and a daemon restart between losing the tmux server and the stop wasn't exercised. (#2962)
  • Codex working counter: a capture that doesn't name its pane keeps the old comparison, a restart that keeps both the pane and its process id isn't seen, and a leftover live frame can count once until it expires. (#2980)
  • Custom blocker IDs explain the wait, but their progress gives no event wake; the timer remains. (#2983)
  • Delivery: delivery evidence records what was known, not that the agent read the message, and events are best effort. A footer row OpenRig doesn't recognize can still hold a delivery (#2925), and a held message's full envelope can stay held; clearing a draft doesn't deliver it (#2515).
  • Runner permission answers were run end to end with a real receiving agent and the example runner, whose requesting agent was a stand-in; a model-driven runner waiting on a person's answer hasn't been run. (#2934)
  • A receiving agent you choose (agents.operator_session) that runs in an explicit or auto permission mode gets no OpenRig allowance for rig host approve or rig host deny, so Claude's review can refuse them.
  • An already-running tmux server keeps its old environment, daemon credentials included, until it restarts. (#2850)
  • herdr-app views are one-shot; following isn't claimed. Pull relay needs a connector that implements pull. (#2744, #2844)
  • From 0.7.12: its known limits still apply, except that #2970 and #2948 are now in this release, runner answers are confirmed and reach a waiting runner at once (#3001), and rig seat stop no longer suggests rig down for an adopted session (#3006). They weren't re-checked for this release unless named here.

Thanks 14

Thank you to everyone whose work is in this release: @Aummadour, @Kayhusk, @Coder8124, @DeryFerd, @EZotoff, @hgreene624, @cavalcanticampos, @ziadeh, @dajiaohuang and @billbenetti.

Thanks also for the reports behind these fixes: @jamesloosli (#2879), @Kayhusk (#2880 and #2951), @CaptObvious (#2948 and #3016), @alperta (#2917), @ziadeh (#2960) and @todd-dhango (#2984).

OpenRig 0.7.12Answer your team in your own words. A reply like "only if it's the test file" now goes to an agent that reads it with the question and decides, instead of being taken as a plain yes.7 added11 changed8 fixed

20 people thanked · Release notes

Highlights

  • ChangedAnswer in your own words: a qualified answer goes to an agent that reads it with the question before anything acts. When no receiving agent is available, your answer waits.

    Your answer goes to an agent. Through 0.7.11 some answers acted on the request directly, and some had no receiver when no operator was set. Now these answers use the configured receiving agent or the kernel operator, with the question included. Answers wait when no receiver is available.

    #2923, #2931, #2934Link

  • Changedrig down now stops only the terminals it started, and names any it left running so you can stop them yourself.

    rig down is more careful. It stops only a tmux session that carries the seat's own OPENRIG_NODE_ID, on the server and session it read. A terminal OpenRig didn't create, a mismarked one or a replaced one is left running, and rig down exits 2 naming it and how to stop it yourself. A seat joined with rig attach as an external CLI is listed as not stopped, since OpenRig never stops it; that alone doesn't make rig down exit 2.

    #2962Link

  • ChangedCodex launches no longer stop at 'Hooks need review' with smol-toml 1.9.

    Codex "Hooks need review" with smol-toml 1.9 no longer needs a manual workaround.

    #2804 · reported by @djuntgenLink

  • AddedCommunity harnesses can speak Pi's protocol, presets can carry launch wrappers, and a seat can switch between Pi and another runtime. A community contribution.

    A community harness can declare protocol: pi-rpc, presets can carry launch wrappers, and a seat can switch between Pi and another runtime. The community-maintained nodecode runner is listed in the reference.

    #2870, #2759, #2669, #2859 · thanks @smota, @seanmcnLink

  • FixedTyped edits in Pi and Oh My Pi seats now submit in the right order on the affected Node releases.

    Pi and OMP: typed edits submit in order on the affected Node releases (22.21.x to 22.22.0, 24.9.0 to 24.11.1, 25.0.0 to 25.1.0) instead of appending an insertion at the end.

    #2847 · reported by @oodadoudouLink

Before you upgrade 2

  • Changedrig down now stops only the terminals it started, and names any it left running so you can stop them yourself.

    rig down is more careful. It stops only a tmux session that carries the seat's own OPENRIG_NODE_ID, on the server and session it read. A terminal OpenRig didn't create, a mismarked one or a replaced one is left running, and rig down exits 2 naming it and how to stop it yourself. A seat joined with rig attach as an external CLI is listed as not stopped, since OpenRig never stops it; that alone doesn't make rig down exit 2.

    #2962Link

  • Changedopenrig-core moves to 0.1.28. If a Codex session you kept running through the upgrade asks for hook approval, relaunch it.

    openrig-core is 0.1.28. A Codex session kept running across the upgrade can ask for hook approval until it's relaunched.

    Link

Also in this release 20

Answering your team 4

  • AddedRegister yourself as your team's person with rig gateway human add. Setup's guidance now asks your agent to offer it, and nothing is registered without your yes.

    Setup's guidance asks your agent to offer to register you as the team's person. In testing the agent didn't reliably make that offer (0 of 5 runs). Registering works when you ask for it: rig gateway human add. Nothing is registered without your yes, an existing default person is kept, and no person is chosen automatically. The empty-registry hint is right. A team you start from your own assistant fits your own logins, with a review before anything is committed.

    #2924, #2905Link

  • ChangedAnswers that used to go nowhere, such as a reply to a host pairing request, now go to your receiving agent or the kernel operator, and wait until one is available.

    Answers nothing else reads, such as a host pairing request or a mode's scheduled end, use the configured receiving agent or the kernel operator. Answers wait when no receiver is available, and nothing decides them meanwhile. To decide one yourself, use its own command: rig host approve or rig host deny for a pairing request, rig seat decide-permission for a runner's request. Closing an ask isn't permission, and words that were kept aren't a default permit.

    #2923Link

  • ChangedAnswer a pairing request in your own words, or decide it yourself in the TUI's pairing settings. The request shows who reads your answer.

    Pairing answers go to the receiving agent, and you can decide directly in the TUI's pairing settings. A pairing request says who it went to and who reads the answer.

    #2931, #2935Link

  • ChangedAnswer a runner's permission request in your own words: an agent reads "only if it's the test file" with the question and decides while the runner waits.

    A runner's permission answer goes to the receiving agent, which decides while the runner waits, so a qualified answer such as "only if it's the test file" is read before anything acts. Your answer is kept and an explicit decision works, but the runner's confirmation updates to you aren't written in this release. Don't expect a confirmation in the Feed, a notice of the receiver's state or an immediate wake: the decision reaches the runner at its next read (up to about 21 seconds in testing). To decide one yourself: rig seat decide-permission <askId> --option <id> --reason "…". This is the runner's path only: a pairing request says who reads the answer, as above.

    #2934, #2938, #2950, #2966Link

Harnesses and connections 2

  • AddedA relay connector that can't accept incoming connections can now pull your team's messages instead: set OPENRIG_RELAY_MODE=pull. A community contribution.

    A relay connector that can't accept incoming connections can pull pending messages for a person instead of being pushed to: set OPENRIG_RELAY_MODE=pull in the relay secrets file. Push stays the default. A person's gateway binding can be unset.

    #2844, #2812 · thanks @w4rc0nLink

  • AddedOpen a Rig view inside the herdr-app desktop window with rig terminal open <view> --provider herdr-app. A community contribution.

    rig terminal open <view> --provider herdr-app opens a Rig view inside the herdr-app desktop window.

    #2744, #2956, #2981 · thanks @w4rc0nLink

Queue, scope and seats 4

  • AddedErase queue content for retention or account deletion, and a retried create can't bring erased work back.

    Queue content can be erased for closed-work retention and account deletion, and a retried create can't bring erased work back.

    #2837, #2843Link

  • AddedEach message now leaves one record of how far its delivery got: what was admitted, what reached the input and what the screen showed.

    Each send records what's known about its delivery in one transport.delivery_evidence event: what was admitted, what reached the input, what the screen check showed, and for which occupant.

    #2937, #2943Link

  • AddedThe queue explains itself: rig queue create flags an unresolved scope, rig queue show names a handed-off task's successor, and a custom blocker says what it's waiting for. A community contribution.

    rig queue create advises on an unresolved scope, slice lists show observed queue counts, a proof policy can require every listed judge, the execution ladder shows each slice's recorded status, rig queue show names a handed-off row's successor, and a custom blocker ID explains the wait.

    #2901, #2902, #2867, #2872, #2874, #2983 · thanks @Aummadour, @dajiaohuangLink

  • ChangedEvery agent's guidance now points to its skills, help and project context, and rig seat status shows when that guidance was written.

    Every seat's managed guidance points to its skills, help and project context. rig seat status shows when guidance was written relative to the session's recorded moments, and what the seat's refocus hook recorded. A rebuilt seat's briefing lists older recaps as optional history.

    #2918, #2920, #2916, #2876Link

Fixes 8

  • ChangedQueue listings, rig queue show and rig parked are faster: they no longer re-read every item. A community contribution.

    Speed: queue listings, rig queue show and rig parked stop re-reading each item; the stuck sweep yields by elapsed time; Markdown section ends are found in one pass.

    #2825, #2926, #2833 · thanks @billbenetti, @oodadoudouLink

  • FixedMessages reach Claude agents more reliably: a custom status line or an update notice no longer blocks a send, and nothing is typed into an open Claude dialog. A community contribution.

    Delivery and drafts: Claude seats with a custom status line read idle and verify sends; a fresh idle hook doesn't type into a current Claude dialog; Claude's context hint and drawn cursor are read correctly; when the input can't be read, a deliberate override (--dangerously-interact) pastes with a warning and doesn't press Enter, so it isn't submitted; update notices beside the paste hint are recognized.

    #2807, #2813, #2947, #2942, #2933, #2800, #2786 · thanks @billbenetti, @KM199 · reported by @CaptObviousLink

  • FixedA message waiting on a Codex choice prompt is delivered once you answer it, and Codex launches no longer stop at "Hooks need review" with smol-toml 1.9. A community contribution.

    Codex: when you answer a Codex choice prompt, a message waiting on it is delivered instead of escalated; a working counter is compared only within one pane process; hook trust records are written under smol-toml 1.9, so launches no longer stop at "Hooks need review".

    #2952, #2980, #2804 · thanks @KM199 · reported by @djuntgenLink

  • FixedRestores and restarts finish cleanly: owed restore input arrives, rig daemon start clears a reservation left from an earlier boot, and a Claude agent resumes the right conversation. A community contribution.

    Restore, start and handover: owed restore input is delivered after a bounded wait on unknown readiness; compaction uses the draft defaults and reports repeated unsent preparation; rig daemon start archives a start reservation left from an earlier boot; the kernel restart guidance describes the existing recovery; an earlier occupant can't replace a Claude seat's resume target; token switches keep the Claude launch; rebuild continuity and Codex launch choices are explained.

    #2818, #2799, #2797, #2915, #2965, #2796, #2853, #2906 · thanks @ziadeh · reported by @KayhuskLink

  • FixedRecovery wastes less of your agents' time: unroutable tasks wake as soon as the agent is reachable, and the stuck sweep reports each finding once. A community contribution.

    Queue and recovery: a polling hosted member (an outside assistant on the team; experimental and off by default) gets one standing notice; a hosted member's ring that times out reads unknown, and durable recovery doesn't repeat that recorded wake (other recovery paths can still ring it again); unroutable items wake as soon as the seat is reachable; the stuck sweep counts a finding once; a handoff doesn't change an escalation's owner; findings route to the seat's own fallback; a park on an outside condition with no wake says so; rig workflow validate is read-only.

    #2864, #2957, #2790, #2824, #2946, #2865, #2851, #2852, #2817, #2763 · thanks @seanmcn, @billbenetti · reported by @todd-dhangoLink

  • FixedSlack is more dependable: threads come back when needed, an ask settles even after its message is deleted, and an unreadable reply says the message "may have posted". A community contribution.

    Slack and people: a Slack reply that can't be read says the message "may have posted"; threads are recovered when needed; an ask settles after its original message is deleted; eligible asks post when quiet hours can't be read, marked when OpenRig can't fully check them; a held ask whose person has no connector closes as no-connector; update delivery is described without assuming Slack.

    #2909, #2788, #2792, #2814, #2805, #2815, #2927 · thanks @seanmcnLink

  • FixedSmaller CLI fixes: rig context recap-write writes where every reader looks, the installer tells you how to fix PATH, and daemon credentials stay out of a tmux server's environment from its next start. A community contribution.

    CLI and config: rig context recap-write writes where every reader looks; config accepts two keys the daemon already resolves; rig whoami says the team is still being built during rig up; rigs with @ in the name find attention; a seat waiting on a person names its question; the installer reports PATH gaps with shell hints; daemon credentials stay out of a tmux server's environment from its next start (a server already running keeps its old environment until it restarts).

    #2914, #2969, #2955, #2949, #2891, #2888, #2883, #2850 · thanks @DeryFerd, @Vaishnavi220506 · reported by @nassersala, @pr0xc3nt4ur1Link

  • FixedA Herdr grid with blank filler cells no longer shows every agent as unconfirmed.

    Terminals: a Herdr grid whose blank filler cells have no label is confirmed, instead of reading every seat unconfirmed.

    #2849 · reported by @pr0xc3nt4ur1Link

Behaviour that changed 2

  • Changedrig down leaves alone any terminal it can't show belongs to the agent.

    rig down leaves terminals it can't show belong to the seat; see Before you upgrade.

    #2962Link

  • Changedrig daemon start now archives a start reservation left over from a reboot, so you no longer clear it by hand. A community contribution.

    A daemon start reservation left after a reboot is archived by rig daemon start; don't clear it by hand.

    #2915 · thanks @ziadehLink

Known limits: 12 for this release. Read them
  • Not in this release: the daemon can pause for up to about a second while reading proof on large mission trees (#2970), and delivery to a Claude seat showing Claude's auto-update failure footer can stall because that footer isn't recognized (#2948).
  • rig down: a terminal it leaves running stays running until you stop it. It doesn't keep a stored host or boot identity, doesn't guard against another program running as you, and a daemon restart between losing the tmux server and the stop wasn't exercised. (#2962)
  • Codex working counter: a capture that doesn't name its pane keeps the old comparison, a restart that keeps both the pane and its process id isn't seen, and a leftover live frame can count once until it expires. (#2980)
  • Custom blocker IDs explain the wait, but their progress gives no event wake; the timer remains. (#2983)
  • Delivery evidence records what was known, not that the agent read the message; where the input ended up can read unknown. Events are best effort, so a missing event isn't proof nothing was sent. (#2937, #2943)
  • Runner permission answers were run end to end with a real receiving agent and the example runner, whose requesting agent was a stand-in; a model-driven runner waiting on a person's answer hasn't been run. (#2934)
  • herdr-app views are one-shot; following isn't claimed. Pull relay needs a connector that implements pull. (#2744, #2844)
  • A receiving agent you choose (agents.operator_session) that runs in an explicit or auto permission mode gets no OpenRig allowance for rig host approve or rig host deny, so Claude's review can refuse them. A kernel receiver in auto mode is included. The default kernel with the default policy passed at its tested scope.
  • A receiver that was stopped and then started may not act on an answer that waited for it. In the tested case where it needed to ask you something back, the question appeared in its own conversation, not in the Feed or Steering.
  • Delivery isn't fixed in general: a footer row OpenRig doesn't recognize can still hold a delivery (#2925), and a held message's full envelope can stay held; clearing a draft doesn't deliver it (#2515).
  • Not run for this release (not run, not passed): the two-seat Codex journey with AGENTS.md restore; Codex account-home, upgrade and continuity checks; the OpenShell worker's second report; Pi model switches on real providers; ACP in a desktop app; Slack directory paging; some Slack setup cases (channel and thread precedence, a stopped receiver's delayed pickup, an inherited inbound default, a plain yes with no receiver); native checks of #2786, #2799, #2807 and #2813, with #2947 partly; a button-and-words answer, a non-pairing ask with an explicit owner, Steering's Approve page, and these answer and setup checks on a default model (the tested runs used smaller models); --wait-for-kernel (#2888), the installed effect of #2800, and #2720 beyond one platform.
  • From 0.7.11: its known limits still apply, except Codex hook setup with smol-toml 1.9.x (#2720), fixed by #2804. 0.7.12 changes openrig-core again, so the Codex hook note there applies to this upgrade too. They weren't re-checked for this release unless named here.

Thanks 20

Thank you to everyone whose work is in this release: @billbenetti, @oodadoudou, @DeryFerd, @Aummadour, @seanmcn, @w4rc0n, @ziadeh, @vanducng, @smota, @sn1thy, @dajiaohuang and @Vaishnavi220506; to @KM199, co-author of #2947 and #2952, which finish their #2513 and #2515.

Thanks also for the reports behind these fixes: @nassersala (#2955), @djuntgen (#2804), @todd-dhango (#2851), @Kayhusk (#2796), @pr0xc3nt4ur1 (#2849 and #2850), @amsayfi (#2776), @oodadoudou (#2847) and @CaptObvious (#2933 and #2942).

Verification and remaining limits

Late verification update: a real Codex lifecycle journey passed its tested launch, same-conversation snapshot restore, existing-rig resume, Core restart with native sessions retained, and fresh-handover task cases. The packaged notes still list that journey as not run because this result arrived after their seal. This does not establish all models or all bidirectional team workflows.

Known limitation: a Codex snapshot restore or rig up --existing can write OpenRig's managed guidance blocks into a tracked AGENTS.md, leaving the worktree modified. Check git status after either operation. Snapshot restore was already disclosed in 0.7.11; the existing-rig trigger is newly observed, and its regression status is not established. A repair is selected for 0.7.13.

The Codex account-home smoke is partial: launch passed, while the account switch was not run after its dry-run requested a named saved profile. Codex ring-2 upgrade coverage and the Codex half of the person-setup checks remain not run at this release decision. The other limitations and coverage omissions in the release notes still apply.

OpenRig 0.7.11Hand work to your OpenRig team from the coding agent you already use. The new openrig plugin works inside Claude Code and Codex, and Zed and T3 Code connect over ACP.12 added23 changed17 fixed

15 people thanked · Release notes

Highlights

  • AddedWork with your team from your own Claude Code or Codex: hand off a task, follow it, answer the team's questions and read the result, with the new openrig plugin.

    The openrig plugin, shipped beside openrig-core, lets a person hand work to their local team from their own Claude Code or Codex, follow it, answer the team's questions and read the result. The plugin's README has the steps. VS Code, Copilot CLI and Cursor install it with no seat. Answers are recorded exactly as typed.

    #2647, #2683, #2709, #2718, #2657, #2733, #2719Link

  • AddedUse your team from Zed or T3 Code: rig acp serve makes it an ACP agent, so a prompt becomes a task and the team's answer comes back as the reply.

    rig acp serve --to <member@rig> runs OpenRig as an agent in ACP apps such as Zed and T3 Code: a prompt becomes a queue task, each task the work reaches shows as a step, the closing resolution is the reply, and the team's questions reach the app while a turn is open.

    #2648, #2714, #2651, #2708, #2686, #2712Link

  • ChangedMessages no longer bounce off a half-typed prompt: they join what's there and go through. To keep the old refusal, rig config set transport.draft_delivery refuse.

    Under the default deliver, an ordinary send or work notice to a seat whose prompt holds a person's typed draft pastes the message at the cursor and submits the combined input, and the result says whether submission was confirmed. Menus, permission prompts, the typing guard, managed compaction and --wait-for-idle still refuse or wait.

    #2645Link

  • ChangedManaged compaction finishes on its own: once prepared, it sends /compact at the next idle moment instead of asking again. A community contribution.

    A prepared managed compaction is held as prepared and sends /compact at the next idle moment instead of asking the seat to prepare again. rig compact --state shows it and --cancel disarms it. Managed compaction also sends /compact under Claude Code's bare update banner.

    #2698, #2716, #2662 · thanks @billbenetti, @Nikhi00718Link

  • FixedOn Linux, restarting the daemon's systemd service no longer takes your agents down, once their tmux server next starts fresh. A community contribution.

    On Linux, a daemon run as a systemd user service starts the seats' tmux server in its own user scope, so stopping or restarting the daemon's unit no longer ends the seats. A daemon started from a login session starts the server as before.

    #2749 · thanks @billbenettiLink

Before you upgrade 5

  • ChangedBack up your database, then install 0.7.11 and restart the daemon: five database updates run on its first start, and going back to 0.7.10 after them isn't established.

    Run npm install -g @openrig/cli@0.7.11, then rig daemon stop && rig daemon start. Back up your database first. Five migrations run at the daemon's first start (150 to 154). With the daemon stopped, copy the file $OPENRIG_DB names. Going back to 0.7.10 after these migrations isn't established.

    Link

  • ChangedOpenRig's own plugin goes to 0.1.27, with updated activity and refocus hooks and three refreshed skills. If you edited its files, check them after upgrading.

    The openrig-core plugin moves from 0.1.26 to 0.1.27. Its activity relay and refocus hooks and three skills changed. The CHANGELOG says replaced files are kept under $OPENRIG_HOME/backups/managed-refresh/<id>/ for reapplying local edits; this release's checks didn't test that route.

    #2756Link

  • ChangedMessages now join a person's half-typed prompt by default. To keep the old refusal, run rig config set transport.draft_delivery refuse.

    Sends now join a person's draft (transport.draft_delivery = deliver). To keep the old refusal, run rig config set transport.draft_delivery refuse.

    #2645Link

  • ChangedA Pi seat can now have its own account home: an absolute PI_CODING_AGENT_DIR in its env: is used as one and needs an auth.json there. A Pi seat that already has its own login can stop at launch, so check those first. A community contribution.

    A Pi seat that declares an absolute PI_CODING_AGENT_DIR in its env: now uses it as its account home and needs a readable auth.json there, or the launch stops. A Pi seat that already has its own Pi login also stops at launch when its spec declares an absolute PI_CODING_AGENT_DIR, even if that folder has an auth.json; the seat's login is kept, and the error names a missing account file rather than the existing login. This is shown by source and function-level tests, not a native run.

    #2630 · thanks @seanmcnLink

  • ChangedOn Linux under a systemd user service, restarting the daemon leaves your agents running once their tmux server next starts fresh; until then, a restart still takes them down. A community contribution.

    Linux, with the daemon run as a systemd user service: the seats move into their own scope only when their tmux server next starts fresh. Until then, stopping or restarting the daemon's unit still takes the seats down.

    #2749 · thanks @billbenettiLink

Also in this release 42

Sends and drafts 3

  • FixedA draft that shows only in the input box is caught before a message is pasted in.

    A draft only the input box shows is caught by one read before pasting.

    #2653Link

  • FixedClaude seats showing a status line or the background task panel no longer confuse draft detection. A community contribution.

    Claude seats showing a statusLine or the background task panel read as a normal composer under the draft-aware guard.

    #2703 · thanks @billbenettiLink

  • FixedA full message backlog no longer drops a sender's later messages, and stopped seats aren't flooded with notices at each daemon start. A community contribution.

    A full held-message quota no longer drops a sender's later messages, and seats stopped while they owe work don't get a burst of undeliverable notices at each daemon start.

    #2701, #2620 · thanks @billbenettiLink

Compaction, restore and handover 5

  • AddedSkills can refresh from their source when a seat is restored: set on_restore: follow_source. A community contribution.

    on_restore: follow_source on a skill refreshes it from its source when a seat is restored; keep_saved stays the default.

    #2626 · thanks @seanmcnLink

  • FixedA seat that's already idle gets its /compact instead of a refusal.

    The final /compact allows for the preparation's own fresh activity (23 seconds, against 9), so a seat that's already idle gets /compact instead of a refusal.

    #2764Link

  • FixedA restore that stops at a prompt, such as Claude's resume picker, clears itself once the seat is back in its conversation. A community contribution.

    A restore stopped at a prompt, such as Claude's resume selection, clears itself once the seat runs the conversation it was restoring.

    #2711, #2674 · thanks @ziadehLink

  • FixedWork notices wait for a compaction's restore request instead of landing right after it. A community contribution.

    A work notice refused at a prompt no longer goes in right after "Compacted" while the compaction still owes its restore request.

    #2666 · thanks @Nikhi00718Link

  • FixedHandovers and restores pick the right conversation: a Codex helper inside a Claude seat no longer becomes its resume token, and Claude rebuilds check their priming packet (the context a rebuilt agent starts from). A community contribution.

    A Codex helper inside a Claude seat no longer becomes the seat's resume token; a Claude rebuild handover checks its priming packet; restoring activity hooks finds the agent's own source.

    #2740, #2650, #2617 · thanks @AummadourLink

Your own coding agent and ACP apps 1

  • AddedAdd OpenRig to an ACP app from the registry: the @openrig/acp launcher runs the matching CLI's rig acp serve through npx.

    The @openrig/acp launcher runs the matching @openrig/cli's rig acp serve for the ACP registry's npx launch, released at the same version.

    #2655, #2715Link

People and connected assistants (experimental, unsupported, off by default) 3

  • AddedAn agent connected through a grant service can see and answer your team's questions, experimental and off by default.

    Assistants connected through a grant service can list and answer the team's questions as a registered person, and --task-destination names the receiver for new tasks.

    #2735, #2638, #2750Link

  • AddedThe relay connector sends your team's questions and updates to a messenger bridge you run and brings replies back, experimental and off by default. A community contribution.

    The relay gateway connector sends questions, updates and notices to an operator-owned bridge over loopback HTTP and takes replies back. The bridge is yours.

    #2624 · thanks @smotaLink

  • AddedAnswer a question right on its card in the web UI's For You feed, experimental and off by default. A community contribution.

    The web UI's For You feed answers a local ask's questions on its card.

    #2612 · thanks @w4rc0nLink

Queue, workflows and status 5

  • AddedQueue commands work across machines with --host, and whoever held a task hears when another machine takes it over. A community contribution.

    rig queue show, list, transitions, update and block take --host <id>; cross-host handoffs that override a claim notify the claimer.

    #2678, #2734, #2621 · thanks @billbenettiLink

  • AddedA code result can name its commits, so rig queue artifact knows what to diff.

    An openrig.code-result/v1 manifest gives rig queue artifact the commit pair to diff.

    #2659Link

  • AddedWorkflows keep their own spec and goal, rig workflow unregister removes old versions, and trace --full shows the whole trail. A community contribution.

    Workflows keep their own spec and root objective, rig workflow unregister removes versions, and trace --full returns the whole trail.

    #2696, #2738, #2676, #2667 · thanks @billbenettiLink

  • ChangedA seat that reads its tasks without claiming them gets one backlog notice instead of one per task, and a claim shows as working while the Claude agent that claimed it runs a background shell. A community contribution.

    One backlog notice replaces a finding per task for a seat that reads without claiming; claims read working while a Claude owner has a live background shell or a managed restore is owed.

    #2752, #2675 · thanks @billbenettiLink

  • FixedA helper harness inside a seat no longer reports its turns as the seat's, and refocus finds projects outside workspace.root. A community contribution.

    A helper harness inside a seat no longer reports its turns as the seat's; refocus traces projects outside workspace.root.

    #2743, #2664, #2717, #2619, #2207 · thanks @MohsintlLink

Launch, install and setup 5

  • AddedMove a Pi seat to another account with rig provider switch, and Pi seats with their own account home start and resume again; the switch is new, so check the seat afterwards. A community contribution.

    rig provider switch --seat <pi seat> --to-account <name> --account-home <dir> --reason "<why>" moves a Pi seat to another account through a confirmed successor (--dry-run shows the plan); in our native run the successor started but the switch wasn't completed, so a completed switch is untested. A Pi seat whose spec declares its account home starts and resumes again.

    #2630, #2782 · thanks @seanmcnLink

  • FixedClaude seats launched with --settings JSON that contains spaces verify again, and launcher scripts that exec Claude's symlink are recognised. A community contribution.

    A Claude seat launched with --settings JSON written with spaces can be verified again, and a Claude launcher script that execs the native installer's symlink becomes ready, with --no-chrome recognised; in our test, 0.7.10 also became ready under the same chain, so this isn't a demonstrated fix.

    #2665, #2751 · thanks @Nikhi00718Link

  • Fixedlaunch_wrapper works for Claude Code, Pi and Codex seats, and a wrapped seat never starts without its wrapper. A community contribution.

    launch_wrapper works for local Claude Code, Pi and Codex seats, and a wrapped seat never starts unwrapped.

    #2746, #2609 · thanks @smotaLink

  • FixedClaude seats that load openrig-core themselves stop loading its skills twice.

    Claude seats that load openrig-core themselves stop loading its skills twice.

    #2660Link

  • FixedSmaller setup fixes: rig attach --self outside tmux, rig host pair --timeout, clearer rig config set warnings, and steadier daemon start and stop. A community contribution.

    Also: rig attach --self outside tmux, rig host pair --timeout, rig config set naming a masking variable, daemon start and stop treating a blocked probe as unknown.

    #2640, #2641, #2692, #2547, #2502, #2643 · thanks @seanmcn, @dajiaohuangLink

Host pairing 4

  • ChangedAnswers to a pairing request now go to the target machine's operator agent, which approves or denies on clear intent and asks back when it isn't sure.

    Answers to a pairing request now reach the target's kernel operator. When the target has an operator that can receive them, typed words and Approve or Deny choices in the TUI, Steering or Slack go to that agent as replies, and receiving one neither grants nor denies access. The operator acts on clear intent with rig host approve <code> or rig host deny <code> and asks back when the answer is unclear. Both commands also work from a plain terminal on the target, using its operator bearer (OPENRIG_AUTH_BEARER_TOKEN, or --bearer <token>). An Approve click on a request the operator owns waits for the operator to act; a stopped operator keeps the request, and the answer waits in its queue.

    Checked on this package: real Slack with a real operator agent in one run (a button or a typed yes approved, a no denied, and a qualified reply got a clarifying question before the refusal denied it); the real TUI without a model (answer credentials, typed answers asked again with no operator, plain-terminal approve and deny, and expiry); and 29 of 29 contained cases with synthetic credentials. Not run: an agent reading answers given in the TUI, Slack thread replies beyond the tested path, and Steering in a browser.

    #2900Link

  • ChangedWith no operator agent to receive answers, Approve and Deny decide directly, and a typed reply gets another ask instead of a denial.

    With no operator, one that can't receive answers, or one OpenRig can't determine, the request says so: Approve and Deny decide directly, and a typed reply gets another ask instead of a denial (the no-operator case was checked; the other two come from the source).

    #2900Link

  • ChangedPairing answers in the TUI use the daemon's operator bearer, and say what to set when it's missing.

    TUI answers use the daemon's operator bearer when one is configured; a missing or wrong one leaves the answer unrecorded and says what to set. Ordinary terminal calls keep their own credential.

    #2900Link

  • FixedSecurity fix: denying a host pairing request now gives the other machine no access. In 0.7.9 and 0.7.10 it could hand over the daemon's access token, so upgrade the machines you pair with.

    Denying or dropping a host pairing request in Steering now gives the requesting machine no access. The problem, that action returning the daemon access token, was found in the 0.7.9 and 0.7.10 source and reproduced with synthetic credentials on an earlier 0.7.11 build.

    #2884Link

Terminals and views 4

  • AddedHerdr follow views work on macOS too.

    Herdr follow views work on macOS too (protocol 22).

    #2663, #2706Link

  • FixedWritable terminal tiles reflow with your screen again, as in 0.7.10, and typing and paste go straight through.

    Writable tiles reflow with the screen: they attach as in 0.7.10, so the screen in use sizes the seat and text reflows on resize, and once attached tmux handles typing and paste directly. Read-only tiles keep showing the seat without attaching, typing into it or resizing it. Fixed web geometry is opt-in (terminal.fixed_geometry, off by default); that browser option wasn't exercised in our checks. Checked in one run in real Herdr 0.9.5 on tmux 3.4 (reflow while viewing, typing and paste once attached, and a tmux window fixed by hand at 80x24), with typing and paste also checked on tmux 3.4, 3.3a and 3.6; phone-size screens and tmux 3.3a weren't run in Herdr.

    #2868, #2757Link

  • FixedClosing the herdr-core terminal that started OpenRig no longer ends the daemon or your seats. A community contribution.

    Closing the herdr-core terminal that started OpenRig no longer ends the daemon or its seats. After merging, @w4rc0n ran a real close with herdr-app 0.1.13 in an isolated Linux sandbox: without the change the daemon, tmux server and seat ended, and with it they kept running. That sandbox had no systemd --user, so herdr-core's service-unit path wasn't run, and a tmux server started inside the terminal before the daemon still ends with it.

    #2737 · thanks @w4rc0nLink

  • FixedTerminal snapshots keep their colours, reattaching during a teardown works, and rig doctor says why tmux control mode is off. A community contribution.

    Terminal snapshots keep colours, a reattach during a broker teardown works, and rig doctor says why tmux control mode is off.

    #2654, #2671, #2633, #2707 · thanks @twotnguyen, @seanmcnLink

Speed under load 3

  • ChangedThe stuck sweep is much lighter on busy installs: each pass takes about half as long, with far shorter stalls. A community contribution.

    The stuck sweep batches its reads: on a copy of a busy 340 MB database, a pass went from about 11 s to about 5 s and the longest stall from about 10 s to 0.57 s.

    #2649 · thanks @billbenettiLink

  • ChangedFewer events pile up: view.changed isn't stored any more, and retention.events_days can prune history-only events, which can't be undone. A community contribution.

    view.changed events are no longer stored, and opt-in retention.events_days prunes eight history-only event types.

    #2695, #2699 · thanks @billbenettiLink

  • ChangedThe web UI loads the newest 100 events, and daemon.seat_poll_interval_ms lets you trade activity freshness for daemon CPU. A community contribution.

    The web UI loads the newest 100 events; daemon.seat_poll_interval_ms trades activity freshness for daemon CPU.

    #2704, #2688, #2636, #2690, #2713 · thanks @billbenetti, @seanmcn, @AummadourLink

Docs and tests 1

  • ChangedDocs and tests: daemon HTTP clients and bearer tokens, the 0.7.10 capability map, a neutral TUI demo snapshot, a web UI editor timer, and test and CI fixes. A community contribution.

    Docs and tests. Daemon HTTP clients and bearer tokens, the 0.7.10 capability map, a neutral TUI demo snapshot, a web UI editor timer, and test and CI fixes.

    #2652, #2736, #2724, #2689, #2753, #2681, #2685, #2673, #2628 · thanks @dajiaohuang, @seanmcnLink

Behaviour that changed 8

  • ChangedSends and work notices that meet a person's draft now join it instead of being refused; rig config set transport.draft_delivery refuse brings the refusal back.

    Sends and work notices that were refused with prompt_draft now go through by default, joined to the person's draft. rig config set transport.draft_delivery refuse restores the refusal from the next send, and under refuse a draft only the input box shows now refuses too.

    #2645, #2653Link

  • ChangedA Pi seat with an absolute PI_CODING_AGENT_DIR uses it as its account home, and won't launch without an auth.json there. A community contribution.

    A Pi seat with an absolute PI_CODING_AGENT_DIR uses it as its account home; no auth.json, no launch.

    #2630 · thanks @seanmcnLink

  • Changed/api/events no longer sends view.changed. A community contribution.

    /api/events no longer emits view.changed.

    #2695 · thanks @billbenettiLink

  • ChangedThe stuck sweep files one backlog notice where it used to file one per task.

    The stuck sweep files one backlog notice where it filed one per task.

    #2752Link

  • ChangedA prepared managed compaction shows as waiting, and a manual rig compact over it reports already_in_progress. A community contribution.

    A prepared managed compaction stays waiting, and a manual rig compact over it reads already_in_progress.

    #2698, #2716 · thanks @billbenettiLink

  • ChangedThe daemon and seats no longer inherit HC_SCOPE, HC_TERMINAL_ID or HC_TERMINAL_SOCKET. A community contribution.

    The daemon and seats no longer inherit HC_SCOPE, HC_TERMINAL_ID or HC_TERMINAL_SOCKET.

    #2737 · thanks @w4rc0nLink

  • ChangedRead-only tiles show a seat without attaching; writable tiles attach as in 0.7.10, and detaching ends only that viewer.

    Read-only terminal tiles show the seat without attaching; writable tiles attach as in 0.7.10, and detaching ends that viewer while the agent keeps running.

    #2757, #2868Link

  • ChangedWith an operator agent on the target, an answer to a pairing request no longer decides it: the operator does, with rig host approve or rig host deny.

    On a target with a kernel operator that can receive answers, an answer to a host pairing request no longer decides it: the operator decides with rig host approve <code> or rig host deny <code>.

    #2900Link

Known issues: 38 for this release. Read them
  • Draft-aware send under Claude Code's update banner: with the draft-aware typing guard, a send to a seat showing the bare ✔ Update installed banner can paste the message and not press Enter, leaving it typed but unsent. Look at the input box before sending again. A fix is on main (#2786) and isn't in 0.7.11. Managed compaction under the same banner sent /compact 3 of 3 times in our test.
  • Unsent compaction preparation: Managed compaction can repeatedly leave its preparation unsent when it cannot read a seat's input box. Inspect the seat; rig compact <seat> --skip-map is the supported manual recovery route, subject to its normal idle and delivery checks; this route was not exercised by the 0.7.11 release checks.
  • A post-compaction step can still hold when the box reads as typed, under draft-aware delivery or the typing guard, or after a lost /compact. Run rig compact <seat> --cancel, then send a restore request naming the newest restore map, marker and packet. A work notice refused at a prompt now waits for that step, but notices at daemon start and on a new handoff don't check for it yet. (#2575, #2666)
  • OpenShell: on OpenShell 0.1.6 the maintained cleanup (delete-owned) now works for a custom image, and recreate and an exact resume passed in our native run. A restored guest takes in its startup content again, so strict recall after a restore isn't met. In our run, finishing the guest's task was assisted and time-boxed, so whether it finishes unassisted is unknown. Never give the guest the daemon's main API port (normally 7433), and after a same-generation reconciled launch, run rig environment connect yourself. (#2755)
  • First users: in one of our three Claude first-user runs, the agent set up the starter team with a Codex reviewer without offering a choice, and a person with only Claude then reached a Codex sign-in. It depends on the agent's choice.
  • rig down can start a duplicate claude --resume for a moment. It's pre-existing and the same on 0.7.10, and we saw no conversation write from it.
  • Herdr follow views: closing a tile when an agent leaves still isn't confirmed, as in 0.7.10.
  • Drafts: detection isn't complete. Under refuse, an unreadable input box lets the send go ahead, so an undetected draft goes with the message; under deliver, a result may not mention a draft it joined. (#2645, #2653)
  • Draft-aware delivery to Claude: a message held as draft_input_unknown still isn't retried. (#2605)
  • Claude provider switch: the last report on #2341, on 0.7.9, fails before any probe pane with "The seat's agent spec (queue.worker) wasn't found where its last launch read it." Its cause isn't established, and 0.7.11 isn't shown to fix it.
  • Pi seats with their own Pi login can stop at launch after upgrading; see Before you upgrade.
  • Host pairing with no operator agent: on a target with no kernel operator that can receive answers, no agent reads a typed answer; it gets another ask, and Approve or Deny decides. An attachment-only reply, or the literal [file reply], keeps no words there and doesn't deny (from the source; not run). (#2900)
  • Host pairing requests live in the daemon's memory, so a daemon restart drops an open request. Receipts, repeat asks and outcomes from clicks reach the requesting machine only while it keeps polling; an explicit rig host approve or rig host deny sends its outcome directly. A request that expires unanswered gets no further update. This comes from the source; no restart case was run. (#2900)
  • Host pairing on older targets: the change is on the machine being paired with, so targets running 0.7.9 or 0.7.10 still treat a typed reply as approval. (#2900)
  • Pi account homes: launch and resume passed in our native run. An account switch didn't complete in that run (the successor started and answered, the test model never confirmed, and the original seat stayed intact), so a completed switch and whether its selection persists are untested. The fix's env -u ordering is tested in macOS CI; for GNU and BusyBox it rests on their documented behaviour, because the Linux CI job doesn't exercise that branch. (#2782)
  • Early writable-tile input: as in 0.7.10, Enter or Ctrl-C typed while a new tile is still attaching can close that viewer. The agent keeps running; reopen the view. This case wasn't exercised in our checks. (#2868)
  • Tiles kept from 0.7.8, 0.7.9 or an earlier 0.7.11 build keep their old client. To refresh one, close only its viewer and reopen the view with rig terminal open; for a --follow view, use --no-follow first, then open a fresh view. The agent and its conversation aren't touched. In our run, kept 0.7.8 and 0.7.9 views kept their process, session and history through the upgrade and the refresh, but they already reflowed before it, so this isn't shown to repair a frozen viewer, and the follow-view upgrade didn't confirm, so it isn't qualified. (#2868)
  • Pi and OMP input order: On Node 22.21.0–22.22.0, 24.9.0–24.11.1 or 25.0.0–25.1.0, cursor-edited text in a Pi or OMP seat can be submitted in the wrong order when keys arrive together, potentially changing its meaning. This also affects 0.7.10. Node fixes are available in 22.22.1, 24.12.0 and 25.2.0, respectively: our input-reader reproduction passed on 22.22.1; the Node 24 and 25 affected ranges and fixes were checked at source, not runtime-tested by us. Real-terminal frequency has not been measured. See #2834.
  • Claude account homes: our checks couldn't verify whether a Claude seat's own account home takes effect, so these notes make no claim about it.
  • keep_saved skills: a skill whose source changes between rig down and the restore comes back missing, named in the restore's warnings; an edited seat copy is kept. (#2626)
  • Read-only terminal tiles each run one tmux command a second while showing: 8 tiles used about 6–8% of one core on an Apple Silicon Mac mini, against about 0.2% for 0.7.10's attached tiles. Writable tiles don't poll. (#2757)
  • rig exec: checked with Claude Code and Codex through their ACP adapters. A cancel is acknowledged, not settled, and says nothing about further spend. Cancel with rig exec cancel, not rig acp cancel.
  • ACP apps: checked in T3 Code (Beta) 0.1.7 on a pre-release build and with a scripted client. The 0.7.11 release checks ran ACP on Claude through acpx 0.15.1, a headless client, not in a desktop app, and the unanswered-question notice hasn't run in a live app. A cancel stops waiting; the work carries on. (#2648, #2686, #2712)
  • The openrig plugin hasn't run in Claude Desktop, the Codex app or Copilot CLI. A seatless app can't claim, update, hand off or answer questions, and everyone using the app on a machine acts as its seat. (#2647, #2657, #2683)
  • Grant-service assistants still aren't notified: a task stays queued until its receiver claims it. Relay: "Accepted by bridge" means the bridge has it, not the person, and a failed send replays only at a restart. (#2735, #2624)
  • Event retention can't be undone, and the database file doesn't shrink. (#2699)
  • Claude launch_wrapper hasn't run with zsh, on macOS arm64 or with a real installed Claude, and an alias or shell function named claude stops the launch. (#2746)
  • Going back to 0.7.10: besides the migrations, an older permission hook gives named-policy Claude sessions no decision until relaunched. (#2640)
  • Codex hooks: a session kept running across an upgrade can show "Hook failed — plugin contents changed; hook approval required" until relaunched, and 0.7.11 changes openrig-core again. rig seat restart --keep-conversation refuses a Codex seat launched with developer instructions (settings_drift), and one started by a 0.6.x tmux-send script (#2200).
  • Codex hook setup: with smol-toml 1.9.x and an existing hooks.json, OpenRig can leave its activity hooks and trust records unchanged. The range (^1.8.0) still permits 1.9.x; the repository lockfile uses 1.8.0. Not fixed in 0.7.11; a fix is on main (#2804) and isn't in this release. (#2720)
  • A Codex snapshot restore writes OpenRig's guidance blocks into a tracked AGENTS.md. Check git status before committing.
  • A scheduled reminder whose delivery fails before input isn't retried; the next occurrence still arrives. (#2478 covers a reminder that never reached its seat; this case remains.)
  • Claude Code 2.1.319 starts in auto mode by default, so a new Claude seat may act without asking; manual mode restores asking.
  • Also: permission requests in seat status show only the latest, in memory for five minutes, and suggested rules can contain sensitive values; Slack private channels need the documented, untested route, direct messages aren't supported and directory reads haven't run live; SSH host status reads unknown behind ProxyJump or ProxyCommand; advisories don't show on a native resume; seats handed over before 0.7.9 refuse stop, restart and clean; after a project-local install, plain rig isn't found in the TUI's own shell; with Claude Code 2.1.319, rig up can wrongly say "Startup prompt still staged … press Enter"; two npm installs into one folder at once once left a partial install, cause unknown.
  • Not run: a Codex first user reaching a finished result (for the third release), the Codex upgrade and journey checks, a Codex account home, the ACP desktop app, an agent reading pairing answers given in the TUI, Slack directory paging, whether a switched Pi account's selection persists, and the 0.7.10 comparison for the tile fix (#2757).

Docs that are out of date in this package (fixed on main)

  • docs/reference/seat-delivery.md says drafts are protected without naming the setting. Under the default, transport.draft_delivery: deliver, an ordinary send that meets a person's draft is joined to it and submitted, unless the seat's typing guard holds input (draft-aware, openrig-urgent, urgent-only or hold).
  • --binding on rig gateway human add is optional, though the CLI reference marks it required.
  • The hosted-members register example needs --delivery-class (for example --delivery-class B).

Thanks 15

Thank you to everyone whose work is in this release: @billbenetti, @seanmcn, @smota, @Aummadour, @dajiaohuang, @w4rc0n, @Mohsintl, @twotnguyen, @ziadeh and @Nikhi00718; to @w4rc0n for running the real terminal close behind #2737.

Thanks to @billbenetti for the reports behind #2752, #2660, #2738, #2749, #2666 and #2665; to @pr0xc3nt4ur1 for the report behind #2740 and #2743; to @oneandonlydean for the process chain behind #2751; to @niklasbaldi for the reports and causes behind #2654 and #2671; to @vadym-abstract-factory for the report behind #2717; to @w4rc0n for the fix and root cause in #2821; to @ziadeh for the reports behind #2622 and #2486; and to @mlc-factory-bot for the reports behind #2605 and #2607.

OpenRig 0.7.10Run a Claude Code or Codex task straight from your queue with rig exec, and a step held after compaction now goes in instead of waiting forever.3 added13 changed11 fixed

13 people thanked · Release notes

Highlights

  • AddedHand one task from your queue to Claude Code or Codex with rig exec run: it runs one turn and reports back, and you decide whether to accept the work.

    rig exec run <row> --harness claude|codex runs one turn through the maintained ACP adapter, in a connector that outlives the command. Use --plan, --wait, status and cancel. One run per row, and --again starts another turn. The outcome is the agent's report. Accepting the work stays with you.

    #2597, #2601, #2596Link

  • FixedA step held after a managed compaction now goes in after two idle polls even when the input box can't be read, instead of waiting forever; rig compact <seat> --state says when that happened.

    After two idle polls that can't read the input box, the held step goes in, and while a later step is still owed, rig compact <seat> --state says the last one went in over a box it couldn't read.

    #2576Link

  • FixedSends now leave any tmux mode, including one a person has open, and a refusal says why.

    Delivery leaves every tmux mode, and a refusal says why.

    #2594Link

  • ChangedThe rigs skill tries a user-writable npm prefix, or a version manager's Node, before a project-local install.

    The rigs skill tries a user-writable npm prefix or a version manager's Node before a project-local install.

    #2611Link

  • AddedSpec advisories show as launch warnings and never stop a launch, and an unknown uses key gets one. A community contribution.

    Spec advisories show as launch warnings and never stop a launch, and an unknown uses key gets one.

    #2606, #2585, #2618 · thanks @dajiaohuangLink

Before you upgrade 4

  • ChangedAfter installing 0.7.10, restart the daemon. There are no database updates.

    Run npm install -g @openrig/cli@0.7.10, then rig daemon stop && rig daemon start. There are no migrations.

    Link

  • ChangedOpenRig's own plugin goes to 0.1.26: it adds a permission-request hook and changes the refocus hook. It keeps a copy of each file it replaces, so reapply any local edit you still need.

    The openrig-core plugin moves from 0.1.25 to 0.1.26. It adds a permission-request hook and changes the refocus hook. Replaced files are kept under $OPENRIG_HOME/backups/managed-refresh/<id>/, so reapply any local edits from there.

    Link

  • ChangedRun rig agent validate <path>: a single-value uses.<category> now selects that resource, so a member fails to resolve if its pool doesn't hold it.

    Run rig agent validate <path>: a single-value uses.<category> now selects that resource, so a member fails to resolve if the pool doesn't hold it.

    Link

  • ChangedIf you run an OpenShell environment, rebuild its guest image with this release's guest.py. Its cleanup still fails against OpenShell 0.1.6.

    OpenShell users: rebuild the guest image with this release's guest.py (see daemon/assets/openshell/README.md).

    Link

Also in this release 18

Compaction, delivery and terminals 3

  • FixedA stale record naming a reused tmux pane no longer stops a send from leaving the mode.

    A stale record naming a reused tmux pane no longer stops a send from leaving the mode.

    #2644Link

  • FixedWritable views size the pane they show.

    Writable views size the pane they show.

    #2614Link

  • FixedHerdr views kept from 0.7.5 to 0.7.9 keep working after upgrading (Linux Herdr 0.9.5): a kept viewer stays confirmed and a follow view goes on adding tiles. Closing a tile when a seat leaves wasn't confirmed.

    Herdr views kept from 0.7.5 through 0.7.9 keep working after upgrading (Linux Herdr 0.9.5 / protocol 22): when only OpenRig's tile script changed, a viewer stays confirmed and a follow view goes on adding and closing tiles. A kept viewer that's already running keeps its earlier sizing for as long as it runs, its own re-attaches included. With a live Herdr after upgrading from 0.7.9, a kept viewer and a follow view's join worked. Closing a tile when a seat leaves wasn't confirmed. It follows @natefaerber's approach in #2467.

    #2634Link

Coordination and status 5

  • Addedrig seat status shows a Claude seat's latest permission request, with suggested rules labelled. Nothing is applied or approved, and suggested rules can contain sensitive values. A community contribution.

    rig seat status shows a Claude seat's latest permission request, with suggested rules labelled. Nothing is applied or approved.

    #2562 · thanks @AummadourLink

  • FixedRouting and status: a send to this host's own ID stays local, rig broadcast says UNCONFIRMED instead of FAILED for an uncertain recipient, refusals for seats handed over before 0.7.9 say why, rig roster reads conflicting activity as unknown, and set-runtime finds pod recaps. A community contribution.

    Routing and status: a send to <seat>@<rig>@<this host's ID> stays local; rig broadcast says UNCONFIRMED, not FAILED, for an uncertain recipient; refusals for seats handed over before 0.7.9 say why; rig roster reads conflicting activity as unknown; set-runtime finds pod recaps.

    #2600, #2572, #2574, #2593 · thanks @Vaishnavi220506, @dajiaohuang, @Nikhila-Dhevi-RLink

  • FixedRefocus names a gap in its trace instead of failing. A community contribution.

    Refocus names a trace gap instead of failing.

    #2582, #2587 · thanks @dajiaohuang, @billbenettiLink

  • FixedThe stuck sweep stops filing informational updates to people as unclaimed work. A community contribution.

    The stuck sweep stops filing informational updates to people as unclaimed work.

    #2586 · thanks @AummadourLink

  • Fixedrig slack status counts cross-host relays still in flight. A community contribution.

    rig slack status counts cross-host relays in flight.

    #2569 · thanks @dajiaohuangLink

Install, specs and errors 2

  • FixedPlain rig works in managed Codex seats however OpenRig was installed, with a Codex that supports allow_login_shell, because tool commands now run in a non-login shell, so login-only shell setup may be missing.

    Plain rig works in managed Codex seats however OpenRig was installed, with a Codex that supports allow_login_shell: tool commands now run in a non-login shell, and rig config set launch.codex_login_shell true defers to Codex's own setting.

    #2613Link

  • FixedClearer errors: a refused terminal token says "Terminal auth failed", the TUI shows the daemon's launch refusal, and rig doctor gives up on a silent listener after 2 seconds. A community contribution.

    Errors are clearer: a refused terminal token says "Terminal auth failed"; the TUI shows the daemon's launch refusal; rig doctor gives up on a silent listener after 2 seconds.

    #2577, #2556, #2564 · thanks @Aummadour, @dajiaohuangLink

Speed under load 1

  • ChangedUnder load, the execution view reads the review registry once per request, queue listings build one recovery index instead of a scan per task, and the event drain reads at most 500 rows at a time. Full listings ran about 63% faster on a test fixture; on a live install that's unmeasured. A community contribution.

    The execution view reads the review registry once per request. Queue listings build one recovery index instead of a scan per listed task. The event drain reads at most 500 rows at a time. On a test fixture, full listings were about 63% faster with the same output. The listing and drain changes are unmeasured on a live install.

    #2578, #2588, #2610 · thanks @billbenettiLink

OpenShell 2

  • ChangedThe OpenShell worker still can't be cleaned up against OpenShell 0.1.6, so recreate and restore can't run yet; its guest now passes the exec's CA settings to Claude and does useful work and a verified export.

    The guest passes the exec's CA settings to Claude, so API calls stop failing with SELF_SIGNED_CERT_IN_CHAIN. TLS checks stay on. With OpenShell 0.1.6 the guest now authenticates, does useful work, makes a verified export and completes its task.

    #2602Link

  • ChangedOpenShell's maintained cleanup still fails against OpenShell 0.1.6. Deleting an environment OpenRig created now reads Podman's inventory, and an unconfirmed cleanup stops as environment_cleanup_unconfirmed.

    Owned-environment deletes read Podman's inventory, and an unconfirmed cleanup stops as environment_cleanup_unconfirmed. The maintained cleanup still fails against OpenShell 0.1.6 (see Known issues).

    #2603Link

Docs and tests 1

  • ChangedDocs and tests: Codex named profiles, openrig-core skill loading, what the runner contract has run, telemetry's guarantee beside the separate, untested openrig-telemetry exporter, and a real-tmux test that waits for the prompt. A community contribution.

    Docs and tests. Codex named profiles, openrig-core skill loading, what the runner contract has run, telemetry's guarantee beside the separate, untested openrig-telemetry exporter, and a real-tmux test that waits for the prompt.

    #2604, #2584, #2592, #2595, #2589, #2559 · thanks @dajiaohuang, @smotaLink

Behaviour that changed 4

  • ChangedA held post-compaction step goes in over an unreadable input box, so an unrecognised draft may receive the restore text.

    A held post-compaction step goes in over an unreadable box, so an unrecognised draft may receive the restore text.

    Link

  • ChangedSends leave any tmux mode a person has open.

    Sends leave any tmux mode a person has open.

    Link

  • Changedrig up can print advisory warnings.

    rig up can print advisory warnings.

    Link

  • ChangedManaged Codex seats run tool commands in a non-login shell, so login- or rc-only setup, shell functions and aliases may be missing, and a model request for login: true gets Codex's refusal.

    Managed Codex seats run tool commands in a non-login shell, so login- or rc-only setup, shell functions and aliases may be missing, and a model request for login: true gets Codex's refusal.

    Link

Known issues: 13 for this release. Read them
  • OpenShell: maintained cleanup (delete-owned) fails against OpenShell 0.1.6, which doesn't mount a workspace volume, so recreate and restore can't run. Never give the guest the daemon's main API port (normally 7433). After a same-generation reconciled launch, run rig environment connect yourself.
  • rig exec: it was checked with Claude Code and Codex through their ACP adapters. A cancel is acknowledged, not settled, and says nothing about further spend. Cancel with rig exec cancel, not rig acp cancel.
  • A post-compaction step can still hold: when the box reads as typed, under draft-aware delivery or the typing guard, or after a lost /compact. Run rig compact <seat> --cancel, then send a restore request naming the newest restore map, marker and packet. (#2575)
  • Draft-aware delivery to Claude still misses the bare ✔ Update installed · Restart to update banner, and a message held that way isn't replayed. Managed compaction can also stop before sending /compact (target_activity_unknown) on a Claude seat showing that banner; in our test, a freshly launched seat once let it through, which isn't a tested fix. (#2605)
  • Claude rebuild: on Linux, a launcher script that execs the native installer's symlink can still lead to a readiness timeout even though Claude is visible. The launch check also does not recognize --no-chrome. This pre-existing issue is not fixed in 0.7.10. (#2341)
  • Permission requests in seat status: only the latest shows, held in memory for five minutes and not persisted across a daemon restart. Suggested rules can contain sensitive values.
  • Codex hooks: sessions kept running across the 0.7.9 upgrade showed "Hook failed — plugin contents changed; hook approval required" until relaunched. 0.7.10 changes openrig-core again. After upgrading to 0.7.10, rig seat restart --keep-conversation refuses a Codex seat that was launched with developer instructions (settings_drift on developer_instructions) and stops nothing.
  • Codex hook setup: with smol-toml 1.9.x and an existing hooks.json in the Codex home, OpenRig can leave its activity hooks and trust records unchanged and log "its trust records couldn't be written exactly". The reporter saw Codex stop at "Hooks need review". The dependency range in this release permits the affected version; our repository lockfile uses 1.8.0. This is a pre-existing issue, not fixed in 0.7.10. (#2720)
  • Slack: private channels need the documented route, which we don't test, and direct messages aren't supported. Channel reads were checked on a live workspace; people (directory) reads weren't. Check errors for a short token fragment before sharing them.
  • Claude Code 2.1.319 starts in auto mode by default, so a new Claude seat may act without asking. In our first-user test, the builder committed after the person asked to be asked first. Switching that seat to manual mode restored asking.
  • A Codex snapshot restore writes OpenRig's guidance blocks into a tracked AGENTS.md, even on Codex 0.164 or later, leaving the working tree dirty. Check git status before committing.
  • A scheduled reminder whose delivery fails before input isn't retried. The next scheduled occurrence still arrives.
  • Also:
    • SSH host status reads unknown behind ProxyJump or ProxyCommand, which doesn't mean the connection is broken.
    • Advisories don't show on a native resume.
    • Seats handed over before 0.7.9 refuse stop, restart and clean until a later launched handover or managed launch.
    • After a project-local install, plain rig isn't found in the TUI's own shell (managed Codex seats are fine). Use the full path.
    • With Claude Code 2.1.319, rig up can wrongly say "Startup prompt still staged … press Enter". Pressing Enter on the empty box adds nothing.
    • In our Codex first-user test, two npm installs ran into the same folder at once and left a partial install (the kernel didn't start, and some files were missing). Which install wrote it, and whether it's new in 0.7.10, is unknown.

Thanks 13

Thank you to everyone whose work is in this release: @dajiaohuang, @Aummadour, @billbenetti, @smota, @Nikhila-Dhevi-R and @Vaishnavi220506; to @AlephCasara, whose work on a fork pointed us to the unpaged event notification drain (#2610), and to @natefaerber, whose approach in #2467 the Herdr view fix follows; and, for reports carried into this release, @billbenetti, @KM199, @ziadeh, @dajiaohuang, @jajabong, @george661 and @aanestesia.

Thanks also to @smota for the OpenTelemetry discussion behind #2589.

Before release we tested the exact package: the private and stock content checks and the release Tests; a real upgrade from 0.7.9 on our own servers; the speed and memory baseline (no worse, slightly faster); the OpenShell worker's sign-in, useful work, verified export and finished task (its cleanup still fails, and recreate and restore weren't run); Slack on a real workspace; a Claude first user from the website to a finished result; Codex first-user setup (plain rig in every Codex seat); and 98 selected broader regression cells (57 passed, 8 had other results, 14 were incomplete and 19 weren't run), with no product regression found. A Codex first user didn't reach a finished result in our test: both attempts stopped on errors in our test setup, so that path's end result is untested.

OpenRig 0.7.9Observations now open work on their own, and a person's typed words reach a runner agent while every default permit is recorded.6 added15 changed5 fixed

40 people thanked · Release notes

Highlights

  • ChangedStream intake is on by default: each rig stream emit opens a queue task for the kernel's queue worker. To keep 0.7.8's behaviour, run rig config set stream.intake off after installing. A community contribution.

    Stream intake is on by default. Each rig stream emit now opens an intake row for the kernel queue worker (queue.worker), or adds a note to the one still unclaimed. The row wakes the queue worker like any queue row, and earlier stream history isn't replayed. To keep 0.7.8's behaviour, with no intake rows, run this after installing: rig config set stream.intake off.

    #2321 · thanks @Totopo27Link

  • AddedA person's typed words on a runner seat's permission ask now count: a plain yes or no answers it; any other words choose nothing, so OpenRig's default permits the request when the agent offered an allow option, and a runner can pass the words to the agent after its turn, never as the answer.

    A person's typed words reach the agent, and the ask says what they do. A reply of just yes or no counts as the agent's allow or reject. "Any other words choose nothing": OpenRig's default permits the request when the agent offered an allow option, and the words come back whole in the read result as said. Section 7 of docs/reference/harness-runner-contract.md lets a runner queue them for the agent "as an ordinary prompt" after the current turn: "They're never the answer."

    #2363, #2561Link

  • AddedEach permit OpenRig grants a runner by default is now recorded, once, as a stream item: read them with rig stream list --tag runner-permission-permit.

    Each permit OpenRig grants by default is recorded, once, as a stream item from the seat: when no one can be asked, and when an ask is closed without a choice (a row passed to an agent seat included). The record names the tool call, why no person answered, the option the agent got with its kind, and the request or ask. Read them with rig stream list --tag runner-permission-permit. A record has no destination, and one that can't be written doesn't change the permit. Stream intake reads past it, so it opens no intake row and wakes no one.

    #2361, #2563Link

  • AddedA working beat keeps a runner's long, quiet turn reading working, and the conformance check no longer falsely fails a correct runner on a busy machine. A community contribution.

    A working beat keeps a long, quiet turn reading working (section 4); a runner that sends none behaves as before. The Pi runner and the dsh example post it, and the conformance check covers it and no longer falsely fails a correct runner on a busy machine.

    #2370, #2336, #2368, #2375, #2530 · thanks @porterchildLink

  • FixedDelivery: fewer messages are held or misdirected on Claude seats, held messages are announced when a seat starts, undelivered reminders retry, and a stalled tmux client ends after 30 seconds.

    Delivery: fewer deliveries held or misdirected on Claude seats (prompt suggestions, wrapped lines, a wake's own paste, the Theme picker, quoted permission questions); held messages are announced when a seat starts or changes occupant; undelivered reminders retry; a stalled tmux client is ended after 30 seconds.

    Link

Before you upgrade 4

  • ChangedAfter installing 0.7.9, restart the daemon: four database updates run on its first start.

    Restart the daemon after installing: run npm install -g @openrig/cli@0.7.9, then rig daemon stop && rig daemon start. Four migrations (146 to 149) run on the first start.

    Link

  • ChangedStream intake is on by default: each rig stream emit opens a queue task for the kernel's queue worker. To keep 0.7.8's behaviour, run rig config set stream.intake off after installing. A community contribution.

    Stream intake is on by default. Each rig stream emit now opens an intake row for the kernel queue worker (queue.worker), or adds a note to the one still unclaimed. The row wakes the queue worker like any queue row, and earlier stream history isn't replayed. To keep 0.7.8's behaviour, with no intake rows, run this after installing: rig config set stream.intake off.

    #2321 · thanks @Totopo27Link

  • ChangedOpenRig's own plugin goes to 0.1.25 and keeps a copy of each file it replaces. Reapply any local edit you still need.

    The bundled openrig-core plugin advances from 0.1.24 to 0.1.25: its seat-continuity-and-handover skill changed. Managed refresh preserves replaced files under $OPENRIG_HOME/backups/managed-refresh/<id>/; reapply local edits you still need from that copy.

    #2420, #2554Link

  • ChangedIf you run an OpenShell environment, rebuild its guest image with this release's helper. The OpenShell worker still doesn't work in 0.7.9.

    If you run an OpenShell environment, rebuild its guest image with this release's helper (daemon/assets/openshell/README.md). An older helper rejects the new startup step, and the error names the rebuild.

    #2418Link

Also in this release 18

Assistants connected through a grant service (experimental) 1

  • AddedExperimental and unsupported. Off by default. Use at your own risk. With a grant service you supply and run, a hosted agent connected over MCP can now work the tasks assigned to its seat in your rig: take one on, add progress notes, set it aside until what it's waiting on happens, and close it with an answer.

    Experimental and unsupported. Off by default. Use at your own risk. This path needs a grant service that you supply and run; ordinary use of OpenRig doesn't need one. With rig mcp serve --http --grant-service <url>, a connected assistant can now claim, update and park the rows addressed to its own seat, and see its team with rig_team, within the scope its existing tools have. Serving MCP over HTTP behind your own tunnel "is like opening a port in your firewall." See docs/reference/hosted-members.md.

    #2384Link

For client authors 1

  • AddedNew daemon reads let a client list people and the default person, read a person's open updates without Slack, and read a rig's messages in one request. A community contribution.

    New daemon reads, two of them by @dajiaohuang: people and the default person, a person's open updates without Slack, a rig's messages in one request, and Slack channels and people without the client holding the bot token. An opt-in decisionRevision lets a client settle exactly the decision its person reviewed. docs/reference/daemon-http-clients.md covers them. The people, updates and messages reads pass their route tests, but no real client used them in our release testing.

    #2495, #2497, #2496, #2501, #2448, #2490 · thanks @dajiaohuangLink

Seats, delivery and the TUI 5

  • AddedOptions and views: specs.builtins_visible: false hides built-in specs, a Claude member's plugin_channels pass to --channels (not yet run with a real channel plugin), and rig context add <url> installs into a new nested name. A community contribution.

    Options and views: specs.builtins_visible: false hides built-in specs; plugin_channels passes a Claude member's plugin channels to --channels (by @Aschenbath, carrying on @todie's fork work), warns beside claude_mcp: none, and hasn't been run with a real channel plugin; rig context add <url> installs into a new nested name; TUI and web UI display fixes.

    thanks @Aschenbath, @todieLink

  • FixedStatus: idle Claude and busy Codex seats read correctly in more layouts, an unreadable pane reads unknown rather than its last verdict, and uncertain sends read unconfirmed.

    Status and receipts: idle Claude and busy Codex seats read correctly in more layouts; stale window samples expire, so a seat whose pane can't be read reads unknown rather than its last verdict; uncertain sends read unconfirmed or indeterminate instead of delivered, lost or failed.

    Link

  • FixedGuidance and handover: an edited culture or startup file reaches the next start, shared CLAUDE.md and AGENTS.md files stop growing, and several Claude rebuild and resume failures are repaired.

    Guidance and handover: an edited culture or startup file reaches the next start, while your own edit to a managed block is kept; shared CLAUDE.md and AGENTS.md files stop growing; handover successors get their guidance and a list of their startup files; several Claude rebuild and resume failures are repaired.

    Link

  • FixedAsks: in a shared workspace, any registered person can settle another's ask and the first answer wins, and Slack records a click on an ask that went back to waiting.

    Asks: in a shared workspace, any registered person can settle another's ask and the first answer wins; a person may have no connector binding; Slack records a click on a re-parked ask and marks asks handled.

    Link

  • FixedInstall and hosts: preflight warns when a Codex seat's login shell can't find rig, rig doctor no longer hangs on a silent port, and upgrade backups work without the sqlite3 CLI.

    Install and hosts: the upgrade skill backs up without the sqlite3 CLI when Node has node:sqlite; preflight warns when a Codex seat's login shell can't find rig; rig host ls reads your ssh config with ssh -G, which runs any Match exec command in it; rig doctor no longer hangs on a port held by a listener that never replies; a scoped launch on tmux 3.4 keeps its default command.

    Link

The OpenShell worker 1

  • ChangedThe OpenShell worker still doesn't work in 0.7.9: in release testing it couldn't reach its model, and deleting an environment it created didn't run. Don't rely on this path.

    The OpenShell worker still doesn't work in 0.7.9. Don't rely on this path. 0.7.9 repairs the layer that stopped it in 0.7.8: in our release testing the guest's agent now starts and reaches its first input. Startup reaches the guest through a hash-checked first-input file, and nothing is typed through the host viewer; the case where the viewer exits wasn't run in our release testing. Readiness checks the guest's own execution, and a failed owned delete reports the stage that failed. Our release testing on 0.7.9 then found two more problems: The worker can't reach its model. The guest's Claude starts, but every API call fails with SELF_SIGNED_CERT_IN_CHAIN. The guest launcher builds a clean environment and leaves out the CA settings the OpenShell exec supplies (NODE_EXTRA_CA_CERTS, SSL_CERT_FILE, REQUESTS_CA_BUNDLE and CURL_CA_BUNDLE). Deleting an owned environment doesn't run. Its inventory step misreads a "Not Found" reply, so the delete is never sent and the owned resources stay. In our test they were removed with the vendor's own cleanup. Attached resources were kept, as intended, and the worker stopped cleanly. With the four CA settings passed through by hand, a worker did useful work; a verified export, an exact restore and a finished task weren't shown. Fixes for both problems are on main (#2602, #2603). They aren't in 0.7.9 and haven't been run end to end.

    #2418, #2404Link

Behaviour that changed 10

  • ChangedStream intake is on by default; rig config set stream.intake off keeps 0.7.8's behaviour.

    Stream intake is on by default (see Before you upgrade).

    Link

  • ChangedFresh Pi seats, and fresh Codex seats on 0.164.0 or later, get OpenRig's guidance outside your repository's AGENTS.md.

    Fresh Pi seats, and fresh Codex seats on 0.164.0 or later, get OpenRig's guidance outside the repository AGENTS.md: Pi in its own agent folder (unless that file or folder is a link), Codex as launch developer instructions. Codex still uses the repository file for a resume, fork, restore or handover successor, an older or unknown version, or a config layer that sets developer_instructions or can't be read. If only your shell startup sets CODEX_HOME, OpenRig reads ~/.codex, so a developer_instructions in your home is replaced for that session; declare the same absolute path as CODEX_HOME in the member's or rig's env: to have it checked.

    #2432, #2441, #2443Link

  • Changedrig down removes OpenRig's own additions from a working folder once no live seat uses them.

    rig down removes OpenRig's own additions from a working folder once no live seat uses them.

    #2387Link

  • ChangedAfter upgrading, the Slack connector marks asks that ended earlier as handled, at Slack's edit rate: about an hour for 450 asks.

    After upgrading, the Slack connector edits asks that ended earlier to show they were handled, at Slack's edit rate: about an hour for 450 asks. rig slack status shows pending edits.

    #2472Link

  • ChangedA later answer to a settled ask gets 409 qitem_already_terminal and records nothing.

    A later answer to a settled ask gets 409 qitem_already_terminal and records nothing.

    #2386Link

  • Changedrig send --verify reports unconfirmed and exits 1 when it can't see what its Enter did. A community contribution.

    rig send --verify reports unconfirmed and exits 1, not delivered, when it can't see what its Enter did.

    #2509 · thanks @dajiaohuangLink

  • Changedrig export with no -o writes rig-export.yaml beside an existing rig.yaml instead of replacing it. A community contribution.

    rig export with no -o writes rig-export.yaml beside an existing rig.yaml instead of replacing it.

    #2356 · thanks @Nikhi00718Link

  • Changedrig workspace validate exits 1 for malformed optional frontmatter. A community contribution.

    rig workspace validate exits 1 for malformed optional frontmatter.

    #2396 · thanks @oodadoudouLink

  • ChangedWhen an active rig name matches more than one rig, rig env lists the matching rig IDs and stops, and rig doctor --spec reports unknown, instead of using the first match. A community contribution.

    An active rig name that matches more than one rig makes rig env down, status and logs list the matching rig IDs and stop, and rig doctor --spec report conformance as unknown, instead of using the first match.

    #2548, #2550 · thanks @dajiaohuangLink

  • ChangedNew default kernels start in <workspace.root>/kernel; existing kernels stay where they are.

    New default kernels start in <workspace.root>/kernel. Existing kernels stay where they are; docs/reference/agent-startup-guide.md describes the optional move.

    #2402Link

Known limits: 16 for this release. Read them
  • OpenShell: the worker doesn't work in 0.7.9 (see The OpenShell worker). 0.7.8's requirements, cost note and cleanup limits still apply, including "Never grant the guest access to the daemon's main API port (normally 7433)." A same-generation reconciled launch opens no viewer, so run rig environment connect yourself; non-text startup actions aren't supported on environment seats.
  • Grant-service assistants aren't woken: "an item stays queued until its receiver claims it."
  • Open updates for a person read a 1,001-row window, so a page can come back short, marked truncated.
  • Slack: a private channel needs the documented route, which we don't test, and direct messages aren't supported. The channel and people reads, and a click on a re-parked ask, haven't been run against a live Slack workspace in our release testing. Redaction of the bot token from a transport error can still leave a malformed token fragment shorter than six characters, so review an error before sharing it. (#2503)
  • SSH host status reads unknown behind a ProxyJump or ProxyCommand; that isn't proof the connection is broken. (#2488)
  • Shared asks: "a click's option written before its answer row … can stand beside or inside the closer's answer without the first clicker's authorship."
  • Existing seats pick up Codex launch instructions and the single skill load at their next fresh launch. A CLAUDE.md or AGENTS.md that already grew isn't trimmed.
  • Permit records last as long as stream retention keeps them. A permit a runner makes on its own, when it can't reach OpenRig, is in its pane only. For an ask opened before 0.7.9, a record may omit the option's kind. (#2361)
  • Draft-aware delivery to Claude: on 0.7.8 with Claude Code 2.1.319, deliveries to idle Claude agents, queue wakes included, were reported held at an empty prompt when a narrow pane showed ✔ Update installed · Restart to update on its own line. 0.7.9 still doesn't recognize that bare banner, though it recognizes /rc and the full versioned banner. A message the draft-aware delivery path holds isn't replayed automatically by that path. (#2605)
  • After a managed compaction, the restore request can stay held. OpenRig delivers each post-compaction step only when it can read the seat's input box as empty. When it can't, it holds the restore request and keeps retrying on its polls, so the seat can sit idle at an empty prompt with its restore not yet requested. rig compact <seat> --state and rig seat status show the restore as owed, and from the second failed attempt the seat's owner gets a queue item naming it. To restore by hand, send the seat a restore request naming its newest restore map, its restore marker and its packet, then settle the owed attempt with rig compact <seat> --cancel; a poll can still race that step. Reported on 0.7.8, and 0.7.9 behaves the same way. (#2575)
  • Seats handed over before 0.7.9 keep their adopted origin until a later launched handover or managed launch records a new session, so until then rig seat stop, restart and clean refuse them as before. (#2440)
  • rig broadcast: an uncertain recipient's outbox receipt now reads indeterminate, but the broadcast's own output for that recipient still says FAILED. Check that seat with rig capture before resending. (#2507)
  • Codex hooks after an upgrade: Codex sessions kept running across the upgrade show "Hook failed — plugin contents changed; hook approval required" until relaunched. In our upgrade test from 0.7.8, one seat restarted with OpenRig's managed restart showed no review afterwards.
  • Codex seats can still report rig: command not found when rig isn't on the login shell's PATH: with Node outside it, or when npm can't install globally and OpenRig is installed inside the project instead. Preflight now warns at launch. In our testing the agents recovered by calling rig by its full path; the getting-started guide describes a ~/.profile fix, which we didn't run.
  • What we ran end to end under the runner contract: this release's dsh example runner, natively, with dsh 0.2.1-rc.2 on DeepSeek's deepseek/deepseek-v4-flash through dsh's pi-ai OpenRouter chat-completions profile, against 0.7.8 Core: two useful queue tasks, queued and multiline input, a quiet tool interval of about 26 seconds that still read working, allow-once and reject-once with their file effects, cancel, a return to the same conversation with recall, and shutdown. The permission answers came from an automated test operator, and the run's preset added resume: true, which the shipped preset doesn't declare. dsh's own DeepSeek Messages route through OpenRouter failed with HTTP 400, and the cause isn't established. Not run: a missing-conversation refusal, cross-host restore, OpenShell, and other adapters, models or providers. 0.7.8's release tests had already run its dsh example end to end, so the 0.7.8 CHANGELOG's "No harness has run end to end under the contract yet" was out of date.
  • Fixed or changed from 0.7.8's limits: the dsh example's env: names, the conformance check's false failures, a person's typed words, the README's operator address, a rebuild behind a symlink, the rebuild receipt, a click on a re-parked ask, and recording a permit made when no one can be asked: a person's answer is recorded on the ask, and a default permit as the stream item above. The other 0.7.8, 0.7.7 and 0.7.6 known limits still apply.
OpenRig 0.7.8A person now answers a runner agent's permission requests, and runners get a conformance check to build against.7 added5 changed5 fixed

20 people thanked · Release notes

Highlights

  • AddedA runner seat's permission requests now reach a person: the default person gets an ordinary ask in the Feed and on Slack, with no setup. rig seat set-permissions-to chooses someone else, a request is permitted when no one can be asked, and refusing is opt-in with --deny.

    A runner seat's permission requests now reach a person, and the default is permit. The runner contract's first version refused every request. Section 7 of docs/reference/harness-runner-contract.md now covers who is asked: With a default person, "They get an ordinary ask in the Feed and on Slack. No setup is needed." To choose someone else, run rig seat set-permissions-to <seat> --to <person> --reason "…". --clear returns to the default. When no one can be asked, the request is "Permitted at once, with the agent's own allow option." Refusal is opt-in, with --deny. "A person's no is never a grant." An unanswered request "stays pending and visible" until the agent's turn ends: "It's never timed out into a grant."

    #2301Link

  • AddedSeats: each OpenRig home can have its own tmux server, a Claude member can opt out of MCP, and rig launch --seats first-starts seats; skill copies, activity hooks and startup declarations are kept across rig down, resumes and exports; and stops are clearer. A community contribution.

    Seats: an isolated tmux server per OpenRig home (rig config set terminal.tmux_server isolated); claude_mcp: none for a Claude member; resuming with a new token file; first starts on rig launch --seats; an accurate account record and kept effort after rig provider switch; skill copies, activity hooks and startup declarations kept across rig down, resumes and exports; clearer stops for handover's fork:<seat>, a missing conversation, claude not found, Codex restart refusals and failed unpins.

    #1260, #2177, #2269, #2342, #2344, #2337, #2338, #2190, #2297, #2287, #2255, #2282, #2330, #2332 · thanks @Aschenbath, @Ethereal49, @AdityaxDeore, @dajiaohuang, @Vaishnavi220506Link

  • Fixedtmux: no crash with OPENRIG_TMUX_CONTROL=1 when control clients end together, and a submit key a read-only client blocks is pasted instead. A community contribution.

    tmux: with OPENRIG_TMUX_CONTROL=1, no crash on tmux 3.3a to 3.7c when the control client ends while another leaves; a submit key that a read-only client blocks is pasted instead.

    #2317, #2325, #2345 · thanks @Aschenbath, @dajiaohuangLink

  • FixedSlack: a typed reply to a decision waiting on you is recorded as the answer, task text renders as Markdown, and resolved decisions stop showing as live asks. A community contribution.

    Slack and usage: typed replies to parked decisions are recorded as answers; row bodies render Markdown; resolved decisions stop showing as live asks; OpenRouter charge retries aren't delayed.

    #2293, #2299, #2316, #2349, #2314 · thanks @dajiaohuang, @ch-davidriott, @Vaishnavi220506Link

  • FixedTUI: agent pages show health and recent work, pod, spec and instance-table views read correctly, and rig terminal open mission:<id> --follow --provider herdr follows a mission. Linux Herdr 0.9.5 only. A community contribution.

    The TUI and views: agent pages show health and recent work; pod, spec and instance-table views read correctly; rig terminal open mission:<id> --follow --provider herdr follows a mission.

    #2263, #2264, #2265, #2266, #2327, #2260, #2289 · thanks @Nikhila-Dhevi-R, @Nikhi00718, @vanducngLink

Before you upgrade 3

  • ChangedAfter installing 0.7.8, restart the daemon: four database updates store new seat settings, among them a Claude seat's MCP opt-out and who answers a seat's permission requests. A community contribution.

    Restart the daemon after installing: run npm install -g @openrig/cli@0.7.8, then rig daemon stop && rig daemon start. Four migrations (142 to 145) store a Claude seat's MCP opt-out, seat activity grants, OpenShell environment bindings and the person chosen to answer a seat's permission requests.

    #2177, #2295, #2296, #2301 · thanks @AschenbathLink

  • ChangedOpenRig's own plugin goes to 0.1.24 and keeps a copy of each file it replaces. Reapply any local edit you still need.

    The bundled openrig-core plugin advances from 0.1.23 to 0.1.24. One line of its seat-continuity skill changed. Managed refresh preserves replaced files under $OPENRIG_HOME/backups/managed-refresh/<id>/; reapply local edits you still need from that copy.

    #2287Link

  • ChangedThe install is larger because the MCP SDK is now needed at runtime, so a clean install runs.

    The install is larger: in the 5 November clean-install check, 0.7.8 resolves to 118 npm packages (including OpenRig itself), against 0.7.6's 32. The MCP SDK is now a runtime dependency.

    #2374Link

Also in this release 9

Permissions for runner seats 3

  • AddedA conformance check tests a runner's answered path. It needs Node and tmux, but no daemon, model, credentials or network.

    A runner conformance check: node docs/reference/runner-conformance/check-runner.mjs --runner '<runner command with {agent}>' --name <harness>. It covers the answered path, and needs Node and tmux but no daemon, model, credentials or network.

    #2303, #2306Link

  • AddedAn example runner for DeepSeek Harness (dsh) comes with its preset to build against. OpenRig doesn't install it.

    An example runner for DeepSeek Harness (dsh), with its preset, is under docs/reference/community-harness-examples/dsh/. OpenRig doesn't install it.

    #2305Link

  • AddedA seat activity grant lets a runner outside the host's hook setup report activity for one seat, without the install-wide hook token.

    A seat activity grant lets a runner outside the host's hook setup report activity for one seat and launch, without the install-wide hook token.

    #2295Link

The OpenShell reference isn't usable in 0.7.8 1

  • AddedThe NVIDIA OpenShell sandbox reference isn't usable in 0.7.8: in release testing its Claude worker never connected, so no work ran. Don't rely on it.

    0.7.8 includes rig environment (setup, create, attach) and a reference for binding a seat to an NVIDIA OpenShell sandbox (daemon/assets/openshell/README.md). In our release testing the worker never became usable: after the sandbox was created and the native process started, rig environment connect failed when its check timed out after 5 seconds, so no team work ran. Don't rely on this path in 0.7.8. The packaged CHANGELOG and What's new describe it as working; this release body replaces them on that point.

    #2296, #2300, #2378Link

Seats, delivery and the TUI 3

  • AddedHosts: rig host edit and rig host remove arrive, OpenRig warns when another user's daemon holds the port, and rig daemon status shows a pending start. A community contribution.

    Hosts and setup: rig host edit and rig host remove; a warning when another OS user's daemon holds the port; rig daemon status shows a pending start.

    #2310, #2346, #2302, #2348 · thanks @DeryFerd, @Vaishnavi220506Link

  • FixedWakes: reminders stop at a full quota, escalations stay deliverable with no person to reach, OpenRig's own Codex hooks are trusted when no choice is recorded, and refusals name their fix. A community contribution.

    Wakes: OPENRIG_WAKE_SUSPEND matches destinations with a colon; prompt escalations stay deliverable without a reachable person; reminders stop at a full quota; human@kernel raises no false finding; OpenRig's own Codex hooks are trusted when no choice is recorded; refusals name their fix.

    #2353, #2343, #2281, #2286, #2294, #2290, #2284, #2280, #2273, #2202 · thanks @dajiaohuangLink

  • FixedAlso: MCP text is cut between whole characters, an ACP cancel survives a failed note, long transcript lines read faster, and Pi and the kernel dashboard get recovery guides. A community contribution.

    Also: MCP text is cut between whole characters; an ACP cancel survives a failed note; long transcript lines read faster; there are Pi and kernel dashboard recovery guides.

    #2268, #2262, #2274, #2186, #2275 · thanks @Nikhi00718, @Vaishnavi220506, @oodadoudou, @dajiaohuangLink

Behaviour that changed 2

  • ChangedA runner that follows section 7 of the runner contract now gets answers or permits instead of refusals; --deny keeps a seat refusing.

    A runner following section 7 gets answers or permits, not refusals. --deny keeps a seat refusing.

    Link

  • ChangedOn tmux older than 3.7c, OPENRIG_TMUX_CONTROL=1 uses spawned clients instead of a control client.

    On tmux older than 3.7c, OPENRIG_TMUX_CONTROL=1 uses spawned clients instead of a control client.

    Link

Known limits: 26 for this release. Read them

Runner seats

  • What we ran end to end: Our Linux release tests exercised dsh-seat 0.3.0 with dsh 0.2.1-rc.2: useful work, a person's allow and deny through the answered path, and cancel. The same dsh-seat session resumed after a managed down/up. The shipped #2305 preset declares no resume; a fresh launch is a new conversation. We did not test another harness end to end under this contract for this release.
  • The dsh example's OPENRIG_DSH and OPENRIG_DSH_HOME aren't accepted in a rig spec's env:. A preset command wrapper that exports them was the route we observed. (Fixed on main, #2414; not in 0.7.8.)
  • Cancel a dsh turn by typing a bare /abort in the pane. A /abort sent with rig send is an ordinary prompt.
  • An in-place keep-conversation restart is Codex-only.
  • The answer owner is a registered person. "A colleague's answer is followed on this host. If the ask is handed to another host, the request waits, shown as needs input, until the agent's turn ends."
  • allow_always from a permit: with no one to ask, "If the agent offers only allow_always, the harness then remembers a permission nobody chose."
  • "Permits and answers aren't recorded beyond the runner's pane and the ask itself."
  • Coming as follow-ups: recording a permit made when no one can be asked, and passing a person's typed words that aren't a plain yes or no to the agent.
  • The dsh example keeps one hold per seat: "if dsh asks twice in one turn, settling one ask releases the hold while the other may still wait on a person."
  • The conformance check can falsely fail a correct runner on a busy machine (case 4b's pending count). Fixed on main; not in 0.7.8.

OpenShell

  • The worker isn't usable (above). The reference also requires NVIDIA OpenShell 0.1.6, a Linux image, and an API-backed provider using ANTHROPIC_API_KEY; subscription or OAuth credentials aren't supported. "Provider registration and image construction can incur costs."
  • The OpenShell README example uses operator@kernel; the actual kernel operator is operator-agent@kernel.
  • "Never grant the guest access to the daemon's main API port (normally 7433)." The guest-only listener is what confines a guest's reach. Its grant only authorizes requests for its own seat and launch.
  • When the viewer's command exits, OpenRig can type the seat's startup text into the host shell, and a line of it can run there as a command. In our test, rig whoami --json ran on the host. The missing check is the same in 0.7.6; environments are a new way to trigger it.
  • Cleanup: delete-owned didn't confirm its delete in our test, and the vendor's own delete cleaned up. A delete still finds the sandbox by name after reading its ID, so a deliberate name replacement in that gap is an open race.

Typing and delivery

  • With the typing guard off (the default for agent seats), an ordinary send submits whatever is in the input box, including a person's unsent draft. rig seat set-typing-guard <seat> --mode draft-aware protects an unsent draft.

Codex seats

  • The alert for a kernel Codex seat stopped at hook review doesn't fire. #2290 added it, but a managed Codex pane runs under a shell, so the check never matches and nobody is told. The review itself still shows in the pane.
  • After an upgrade, Codex seats that kept running show "Hook failed — plugin contents changed; hook approval required" and lose refocus until relaunched.
  • With Node installed outside the login PATH (seen with an /opt tarball), a kernel Codex seat can report rig: command not found. In our first-user test, asking the agent to fix PATH recovered it.

Claude seats

  • For a Claude installed at a custom path not named claude, a provider switch can't read the running effort (it uses the authored effort, and says so), and rig down may briefly run a resume probe.
  • On macOS, after a daemon restart, rig seat continue can refuse a healthy auto-mode Claude seat with attention_required. Ordinary sends still work.
  • A rebuild still waits when the running Claude's command is a symlink to the launched binary (the case reported in #2341). The repair is on main; not in 0.7.8.

Handover and Slack

  • The rebuild-handover receipt reports provenanceRecordWritten and departingSessionKilled as false even when both happened, so don't re-run a handover on those two fields alone. (Fixed on main, #2420.)
  • A button click on an ask its owner re-parked is answered "Already answered", and resumes the owner with the earlier answer without a wake; a typed reply records a new answer. (Fixed on main, #2421.)

The packaged notes

  • The packaged CHANGELOG and What's new still say 0.7.7 isn't published. It was published on November 2. They also describe the OpenShell reference as working (above), and the capability map says a typed reply to a question parked on its own person isn't recorded as the answer, which 0.7.8 now does (#2293).
  • The 0.7.7 and 0.7.6 known limits still apply.

Thanks 20

Thank you to everyone whose work is in this release: @Aschenbath, @dajiaohuang, @Vaishnavi220506, @Nikhila-Dhevi-R, @Nikhi00718, @oodadoudou, @DeryFerd, @ch-davidriott, @vanducng, @Ethereal49, @AdityaxDeore and @Mydudeclaps; to @bpamiri for dsh-seat, whose fake agent the conformance check's stand-in follows; and, for reports carried into this release, @salbang, @ziadeh, @davey64, @bpamiri, @oneandonlydean, @xwcq, @seanmcn and @AlexGhanem.

OpenRig 0.7.7Reliability fixes for Claude seats, including compaction that doesn't type over an unsent message.1 changed4 fixed

1 person thanked · Release notes

Highlights

  • FixedManaged compaction no longer types into a message you haven't sent: it checks the input box first and holds the step, saying why.

    Managed compaction no longer types into a draft. With the optional typing guard off (the default), compaction's preparation prompt could be pasted onto a message someone had typed but not sent. Now the preparation prompt, /compact and the restore prompts check the input box first: typed or unreadable input holds the step with a reason. A held restore prompt goes ahead on its own once the box is empty; a manual rig compact says why it stopped, to be retried once the box is empty. An empty box or Claude's own suggestion goes ahead.

    #2347Link

  • FixedA Claude agent at an empty prompt under Claude's 'Update installed' line reads idle again, so managed compaction no longer waits on it.

    A Claude seat under the "Update installed" line reads idle again. After Claude installs an update, it prints "✔ Update installed · /restart to apply" (or "Restart to apply") below its mode bar. OpenRig didn't recognize that line, so a seat at an empty prompt read unknown instead of idle, and managed compaction waited. Both spellings are now recognized; lines that only look similar still read unknown.

    #2311Link

  • FixedA Claude agent started through a wrapper script can be rebuilt with a handover again, instead of stopping after 30 seconds.

    A Claude seat launched through a wrapper script can be rebuilt again. On 0.7.6, rig seat handover --source rebuild on a seat whose claude is a #! script that starts the real Claude without exec stopped after 30 seconds with "Waiting to confirm the new Claude process in this pane", though the new Claude was running. The readiness check now also accepts the script's own direct child when it names this launch's conversation; every other check is unchanged.

    #2354 · reported by @oneandonlydeanLink

Before you upgrade 1

  • ChangedAfter installing 0.7.7, restart the daemon so the fixes take effect. There are no database updates, and OpenRig's own plugin is unchanged.

    Restart the daemon after installing so the fixes take effect: run npm install -g @openrig/cli@0.7.7, then rig daemon stop && rig daemon start. There are no database migrations. The bundled openrig-core plugin stays at 0.1.23 with unchanged files.

    Link

Also in this release 1

Claude 1

  • FixedA failed handover no longer moves the agent's resume target to the new, unprimed conversation.

    A failed handover no longer moves the seat's resume target to the new, unprimed conversation while the seat keeps its previous occupant.

    #2354Link

Known limits: 5 for this release. Read them
  • The symlink-launch case reported in #2341 is not covered by the wrapper fix. When the running Claude's command names a symlink but OpenRig recorded the resolved binary, source inspection shows that readiness still rejects that combination. The exact reported launch sequence has not been reproduced, and why it retains the symlink path is still under investigation. This is not a failure of every native-installer launch.
  • Other reasons managed compaction can wait are unchanged.
  • The draft check reads the input box just before pasting. Typing that starts in the same moment can still be appended to.
  • A Claude seat whose current occupant generation was never registered, such as an adopted Claude carrying another generation, or a managed launch whose tenure record failed to write, keeps its first conversation token, but later hooks don't move it.
  • The 0.7.6 known limits still apply.

Thanks 1

Thank you to @oneandonlydean for the report and the evidence in #2341.

OpenRig 0.7.6Move an agent to another account with a handover, and follow a whole slice's work in one terminal workspace.7 added6 changed7 fixed

16 people thanked · Release notes

Highlights

  • Addedrig provider switch moves a running agent to another account home, with a fresh conversation and a handover; it keeps its address and work. A community contribution.

    Move a running seat to another account home with rig provider switch --seat <seat> --to-account <name> --account-home <dir> (preview with --dry-run). It starts a fresh conversation with a handover, and the seat keeps its address and work.

    #2143 · thanks @seanmcnLink

  • AddedFollow a slice's work in one terminal workspace: rig terminal open slice:<name-or-id> --follow --provider herdr shows the agents with open work in that slice, each once. Linux Herdr 0.9.5 only.

    rig terminal open slice:<name-or-id> --follow --provider herdr shows the current owners of the slice's open work: pending, in-progress and blocked queue rows tagged with that slice. Each owner appears once, with all its obligations listed. Tag a row with rig queue create --slice <name-or-id>; handoffs keep the tag.

    Slice following targets Linux Herdr 0.9.5 / protocol 22. Following a whole mission isn't in this release.

    #2259Link

  • ChangedWhen only the readiness deadline passes, rig daemon start says startup is pending and leaves the daemon running, instead of killing it.

    Startup: when only the readiness deadline passes and the daemon is still starting, rig daemon start exits nonzero with a pending message naming the process, its endpoint and the log. The daemon is left running, and a second start stays blocked. rig daemon stop can't reach that unpublished process; the message gives the manual restart.

    #2267Link

  • FixedA queue wake refused at a selection prompt is retried once the prompt clears, and work sent to a terminal-only agent raises a finding for a person.

    A queue wake refused at a selection prompt is retried once the prompt clears. Work sent to a terminal-only seat raises a finding for a person. Cross-host rig queue create --verify reads the destination's receipt.

    #2235, #2192, #2193Link

  • FixedA Slack button answer now resumes a decision waiting on the person asked, and --reactions off stops acknowledgement emoji waking agents.

    A Slack button answer now resumes a decision parked on the person asked, which was 0.7.5's known issue. rig slack setup --reactions off stops acknowledgement emoji from waking agents.

    #2245, #2241Link

Before you upgrade 3

  • ChangedAfter installing 0.7.6, restart the daemon: two database updates record a seat's account home and whether a harness launch declared a runner.

    Restart the daemon after installing: run npm install -g @openrig/cli@0.7.6, then rig daemon stop && rig daemon start. Two database updates record a seat's selected account home and whether a community-harness launch declared a runner.

    Link

  • ChangedOpenRig's own plugin goes to 0.1.23 and keeps a copy of each file it replaces. Reapply any local edit you still need.

    The bundled openrig-core plugin goes to 0.1.23: its Claude activity hook now clears permission marks after a tool batch. Replaced files are preserved under $OPENRIG_HOME/backups/managed-refresh/<id>/; reapply any local edits you still need.

    Link

  • ChangedOn a large database, rig daemon start may report that startup is still pending. Follow the guidance it prints before any recovery.

    On a large database, rig daemon start may now report that startup is still pending instead of failing. Follow the guidance it prints before trying any recovery.

    Link

Also in this release 12

Follow a slice's work 5

  • AddedA slice view starts with four tiles, keeps following when the slice is empty, and keeps its viewers when a read is incomplete.

    New slice views start with four automatic tiles; --max-tiles changes that. A known empty slice keeps following and fills again. An incomplete read keeps the previous viewers, and missing or ambiguous slices are named, never shown as an empty team. Pins, drafts, unknown input and focus still protect a departed viewer, and closing a viewer never stops its agent.

    Link

  • AddedWhen a slice's name repeats across missions, tag its work with the slice's unique id, or the view reads incomplete.

    When a slice's folder name repeats across missions, tag its work with the slice's unique ID (or add --mission). A row tagged only with the shared name can't be placed, so the view reads incomplete until it is.

    #2261Link

  • ChangedSlice following is for Linux Herdr 0.9.5. Following a whole mission isn't in this release.

    Slice following targets Linux Herdr 0.9.5 / protocol 22. Following a whole mission isn't in this release.

    Link

  • FixedAn agent whose pane was refused before any split joins on a later refresh, and a viewer that hasn't attached yet can carry on.

    An owner whose join was refused before any pane split now joins on a later refresh, and a viewer that hasn't attached yet can carry on.

    #2271Link

  • FixedNamed Herdr sessions use their configured endpoint throughout, and the TUI's terminal action opens what's in view.

    Named Herdr sessions use their configured endpoint throughout, and the TUI's terminal action opens the agent, pod or rig in view.

    #2205, #2232Link

Seats, accounts and harnesses 4

  • AddedA Claude agent can switch between its subscription and an API key on the same conversation. The API-key path is not qualified yet, so check the result. A community contribution.

    A Claude seat can switch between subscription and API key on the same conversation (--to-account api --api-key-file <file>, back with --to-account plan --token-file <file>). In-flight work is interrupted. The API-key path is not qualified yet, so check the resulting account and conversation. A new Claude member can name its own token file in its spec with claude_token.

    #2191, #2246 · thanks @seanmcnLink

  • AddedManaged agents use the daemon's SSH agent for git over SSH.

    Managed seats inherit the daemon's SSH agent for git over SSH.

    #2222Link

  • AddedCommunity harnesses can opt into following their runner and receiving the declared model. New draft author contracts describe harness, runner and platform duties.

    Community-harness presets can opt into runner: true (with launch_result: true) so the seat's activity follows its runner, and passes_model: true to receive the declared model as OPENRIG_MODEL. That says which model was passed, not which one runs. New draft author contracts describe harness, runner and platform duties, marking what's implemented and what's proposed.

    #2239, #2243, #2272Link

  • Fixedrig expand keeps the member settings rig up accepts, and a restore keeps a model set with rig seat set-model.

    rig expand keeps the member settings rig up accepts, including env, effort and startup settings, and a restore keeps a model set with rig seat set-model.

    #2250, #2227, #2228Link

Behaviour that changed 1

  • ChangedThe viewer API returns HTTP 400 for view_required and unknown_provider, where it returned 200 with an error body.

    Viewer API: POST /api/terminal/viewer/ensure returns HTTP 400 for view_required and unknown_provider, where it returned 200 with an error body. Keep reading the body's code.

    #2259Link

Delivery, Slack and status 2

  • FixedAn exited process in a kept pane reads as exited, not idle, and its work goes to the usual recovery finding.

    A verified exited process in a retained pane reads pane_exited, not running and idle, and its work goes to the usual recovery finding.

    #2248Link

  • FixedSmaller fixes to inventory reads, UTC snapshot ages, TUI emoji, help text and test fixtures.

    Smaller fixes cover inventory reads, UTC snapshot ages, TUI emoji, help text and test fixtures.

    Link

Known issues: 7 for this release. Read them
  • Codex hooks on an older configuration (#17): if your Codex configuration came from an older OpenRig install that never trusted OpenRig's own plugin hooks, after a restart the kernel's Codex seats can stop at Codex's "Hooks need review" prompt. rig status then shows the kernel as partial_ready, and rig ps shows the seats needing attention. No message is sent. This also happens on 0.7.5.
  • An exited viewer isn't restarted: a viewer whose attach already ran and then exited back to a shell isn't restarted automatically, and the whole slice view can hold until that tile is resolved. No tested workaround is offered yet.
  • Later hold notices can show a generic reason; the original failure is in the journal. The changelog's and capability map's statement that hold notices retain the original reason holds for a seat's first notice, not for every later one.
  • A typed reply in the thread of a question parked on its own person resumes the question, but isn't recorded as the answer; the owner receives it as a message instead. Buttons work. The capability map's statement that a typed Slack reply is kept in humanAnswers doesn't hold for such a parked question.
  • Held is not delivered: with a Codex seat's typing guard on, a message OpenRig can't confirm will stay visible is held before it's pasted. That can happen in small tiles, and many wrapped messages are held even when they would have fit. Check rig seat held-messages before resending. A larger pane or a shorter message may help; turning the guard off removes draft protection and isn't a fix.
  • Codex restart refusal (#2200): it's still unresolved. If rig seat restart <seat> --keep-conversation refuses, nothing is stopped; leave the seat running and report it with your CLI and daemon versions.
  • Hosted members remain experimental, unsupported, off by default and at your own risk. Slice following doesn't need them.

Thanks 16

Thank you to everyone whose work is in this release: @seanmcn, @DeryFerd, @Aschenbath, @Vaishnavi220506, @bradvin, @jay23606, @rudycelekli and @Nikhi00718; to @akushonkamen, @jcmurrayii, @KM199 and @pdurlej for changes, reports and reproductions that shaped it; to @appleguy, @al-robertson-cto and @skv-io, whose reports led to fixes and documentation here; and to @bpamiri, whose runner-preset proposal on #43 shaped the runner field.

OpenRig 0.7.5Follow a task's agents as terminal tiles (preview), and escalations now reach someone who can act.3 added7 changed8 fixed

12 people thanked · Release notes

Highlights

  • AddedPreview, Linux Herdr 0.9.5; usually one agent: rig terminal open qitem:<id> --follow --provider herdr keeps the agents working on a task together in one Herdr workspace.

    rig terminal open qitem:<id> --follow --provider herdr shows the current owners of a task's open work as viewer tiles in one Herdr workspace. Joining agents get viewer tiles; departures close viewers, not agents or conversations. --pin, --suppress and --max-tiles adjust the view; --no-follow keeps a fixed layout. Defaults are eight tiles, four seconds of departure grace and twelve more seconds for a focused leaver.

    The preview is limited to Linux Herdr 0.9.5 / protocol 22 and requires no internet exposure.

    #2199Link

  • Fixedrig send waits up to 60 seconds for its result. An unconfirmed send may still have arrived, so check before sending again.

    rig send waits up to 60 seconds for its result, locally and over HTTP, plus a requested idle wait. A send can still read unconfirmed sooner, for example when a connection drops. An unconfirmed send may still have been delivered; input may be held off-screen by a busy recipient. Reconcile before resending. No automatic resend is added.

    #2198Link

  • FixedA protected Codex agent holds a message it can't show whole before typing it, so nothing is left typed and unsent.

    With a Codex seat's typing guard set to draft-aware or openrig-urgent, a message OpenRig can't confirm will stay visible in the composer is held before it's typed, so nothing is left typed and unsent. A message that fits is delivered and submitted once, and a person's draft stays protected. The default (guard off) and other runtimes are unchanged. Delivery's guards also recognize Codex 0.164's two-row composer footer, so a truly empty Codex 0.164 composer can receive typed delivery.

    #2242, #2206Link

  • FixedA wake that couldn't be routed is tried again once the agent has a pane, and stuck-work findings need evidence to close. A community contribution.

    A wake recorded as unroutable is retried through its existing intent once the seat has a pane; stuck findings require delivery or custody evidence to close.

    #2170, #2153 · thanks @AschenbathLink

  • FixedA fresh Claude handover waits for the new process, and rig down after a rolled-back launch stays down. A community contribution.

    Fresh Claude handovers wait for the new process and its current input frame. A rolled-back launch followed by rig down stays down on rig start --last.

    #2159, #2166 · thanks @AschenbathLink

Before you upgrade 3

  • ChangedAfter installing 0.7.5, restart the daemon: one database update keeps existing edges, and an escalates_to edge that did nothing before now takes part in recovery for an agent with no delegation parent (no agent that hands it work).

    Restart the daemon after installing: run npm install -g @openrig/cli@0.7.5, then rig daemon stop && rig daemon start. A database update stores deferred escalation addresses while preserving existing edges. Previously inert escalates_to edges now affect recovery for seats without a delegation parent.

    Link

  • ChangedStartup refreshes OpenRig's own plugin to 0.1.22, keeping a copy of each file it replaces. Reapply any local edit you still need.

    Startup refreshes openrig-core to 0.1.22. Its queue-handoff skill teaches agents to park long waits with a continuation and wake. Replaced files are preserved under $OPENRIG_HOME/backups/managed-refresh/; reapply local edits you still need. No setting is added or removed.

    Link

  • ChangedIf Codex asks for hook review, review the hooks you mean to enable, and read #2200 before relying on the restart remedy.

    If Codex requests hook review, review the hooks you intend to enable. The earlier hook-refresh remedy, rig seat restart <seat> --keep-conversation --reason "refresh hooks" (preview with --plan), has an unresolved refusal report; read #2200 below before relying on it. Upgrading does not restore approvals an earlier OpenRig removed.

    Link

Also in this release 10

Seats & restore 1

  • ChangedRecovery for an agent with no delegation parent (no agent that hands it work) can use an escalates_to address in another rig on the same daemon. A community contribution.

    Parentless recovery can use an escalates_to address in another rig on the same daemon. A delegation parent still wins; an open recovery keeps its recorded owner.

    #1772 · thanks @icey-zzzLink

Queue & messaging 1

  • ChangedRuntime send refusals answer 409 instead of 500, and a stale Claude pane names rig reconcile-session as the fix.

    Runtime send refusals return HTTP 409 instead of 500. A stale Claude pane names rig reconcile-session <seat> as the repair.

    #2157Link

TUI 2

  • ChangedFollowing keeps departed tiles that hold a draft or unreadable input, and stops once an empty task has no tiles left.

    Follow mode retains departed tiles with drafts or unreadable input. A completely empty task drains removable tiles and stops following once none remain; run --follow again to resume that workspace.

    Link

  • FixedThe Overview reads the selected rig's current setup, the TUI uses your local host name, and snapshot status matches the scheduler. A community contribution.

    The Overview reads the selected rig's current configuration; the TUI uses the configured local host name; snapshot status matches the scheduler.

    #2188, #2162, #2168 · thanks @dajiaohuang, @Aschenbath, @todieLink

CLI & hosts 1

  • FixedOpening terminals now says when a pane can't be confirmed, and an all-unconfirmed open fails so you check first.

    Terminal results distinguish pane_unconfirmed from opened and skipped panes. An all-unconfirmed open exits nonzero; inspect before retrying because something may have opened.

    #2173Link

Setup & platform 1

  • FixedSmaller fixes: a pi-tui example, clearer hosted-member guidance (hosted members stay experimental, unsupported, off by default and at your own risk), and tmux, capture, port and scope-folder repairs. A community contribution.

    The pi-tui example runs Pi's own terminal UI with a per-seat agent folder and startup input. Hosted-member guidance says how a member without a wake trigger gets work, that a listed tool is not a grant, and that finished work closes with no-follow-on. Other changes repair tmux separator parsing for attach --self replies, normalize capture/transcript line counts, warn on invalid MCP daemon ports, release unread notification response bodies, and accept scope folders numbered 100 and above.

    Hosted members retain 0.7.4's framing: experimental, unsupported, off by default and at your own risk. Local assistants can connect locally. Internet access requires your own TLS tunnel or proxy and a narrowly scoped token; anyone holding a valid token can act within its grant. Revoke it when finished with rig mcp token revoke <name>.

    #2182, #2187, #2178, #2164, #2160, #2172, #2194 · thanks @DeryFerd, @Nikhi00718, @rudycelekliLink

Preview: follow one task in one terminal workspace 4

  • AddedPreview, Linux Herdr 0.9.5; usually one agent: following an ordinary task shows the one agent working on it, then the next agent after a handoff.

    What you'll usually see is one agent. A queue item has one owner at a time, and handing it off closes it, so following an ordinary task shows its current owner, replaced by the next owner after a handoff. Several agents appear together only when several open rows descend from the task at the same time, by handoff or by naming it in their chain of record.

    Link

  • AddedPreview, Linux Herdr 0.9.5; usually one agent: a client can add or reuse a viewer without rearranging panes; being in the view grants no input.

    Clients can add or reuse a verified viewer without rearranging existing panes through POST /api/terminal/viewer/ensure. Membership grants no input authority.

    #2133Link

  • ChangedPreview: following a slice or a mission isn't in this release.

    Following larger scopes of work, such as a slice or a mission, isn't in this release.

    Link

  • FixedPreview, Linux Herdr 0.9.5; usually one agent: a departed Codex agent's empty composer no longer keeps its tile.

    The view recognizes Codex 0.164's two-row composer footer, so a departed Codex agent's empty composer no longer reads as unconfirmed input that keeps its tile.

    #2206Link

Known issues: 8 for this release. Read them
  • A protected Codex message can be held in a small tile (#2242): with a Codex seat's typing guard set to draft-aware or openrig-urgent, OpenRig holds a message before pasting it when it can't confirm the whole message will stay visible in the composer. That can happen in small task-following tiles, and many wrapped messages are held even when they would have fit. A held message is not delivered. Use a larger pane; a shorter message may also fit; turning the guard off removes draft protection and is not a fix. A very long message (over 1,000 characters) is held whatever the pane size, so shorten it.
  • A Slack button answer to a parked question isn't recorded. If a question waiting on you has been parked by its owner, a button answer to it isn't recorded, and the reply wrongly says the decision is no longer waiting. Other ways of answering a parked question weren't tested in this release. A repair is on main.
  • Codex restart refusal (#2200): reported on one upgraded Codex seat; the cause is unknown, and it is not fixed here. The inspected 0.7.4 check already accepts the reported process tree, so this is not an established refusal of all 0.6.x staged-script launches. If refused, leave the seat running and report the refusal with CLI and daemon versions; don't count it as a completed hook refresh.
  • A named Herdr session can miss a custom daemon endpoint. With --session <name>, OpenRig may resolve Herdr's default socket location rather than a custom endpoint your daemon is configured to use. The configured endpoint works without --session. To reach a specific endpoint, set HERDR_SOCKET_PATH to it explicitly; don't rely on XDG_CONFIG_HOME, which the default resolver doesn't read.
  • Unreadable composers keep departed tiles, including unconfirmed Pi, terminal and community-harness input. Unpinning does not override this. Other providers, platforms and selectors retain one-shot open. A viewer can resize its agent's terminal; ignore-size is not isolation.
  • Run pi-tui unattended, without typing into it: a wake can submit a draft someone is typing or enter an unrecognized dialog. Busy-turn wakes and native resume remain unqualified; a plain terminal receives no queue wakes. See the example's limits.
  • Cross-rig escalation is same-daemon only. Upgrade followed by snapshot restore of deferred targets remains unqualified.
  • Existing harness limits remain: OpenClaw's interrupted local turn is not recovered; use its Gateway preset for unattended work. Hermes declares no resume, and its idle gateway exit is unmeasured. rig down stops a community harness's pane; inspect any independently spawned processes before relying on their exit.

Thanks 12

Thank you to everyone whose work is in this release: @icey-zzz, @Aschenbath, @DeryFerd, @Nikhi00718 and @dajiaohuang; to @rudycelekli for the work completed in #2160 and @todie for the snapshot-status change followed in #2168; and, for reports, @agraubert, @AdamWhitehurst (#1544, #2049), @kevinhsykes (#2151), @aanestesia (#605), @todie (#1419) and @tgrundtvig (#21).

Verification limits

Task following was checked with real agents on Linux Herdr 0.9.5: tiles joined and left as genuine work moved (3 → 4 → 3), a focused leaver stayed briefly before closing, a person's typed draft survived a join, the tile cap, pins and suppression behaved as described, and turning following off and on again kept the same agents. The empty-task stop was confirmed from the recorded events, and on screen in a recorded run. Resource use was measured only as whole-machine CPU in one window, not for the daemon alone.

Performance against 0.7.4 was measured on an earlier build of this release, on one machine, with a synthetic workload: no measured change in command latency, memory or CPU.

Protected Codex delivery (#2242) was checked with real Codex agents: a fitting message at 80×24 was submitted once (a model reply was not checked), in a 30×9 pane it was held before paste in both guard modes, and at 32×9 a person's unsent draft was kept in both modes. The 65×9 tile, messages with hard line breaks, and very long messages were not run natively.

OpenRig 0.7.4OpenRig 0.7.4 takes a first, experimental step toward every agent you use working on one team.5 added1 expanded2 changed4 fixed

12 people thanked · Release notes

Highlights

  • AddedA first, experimental step toward hosted agents working on one team. Unsupported and off by default; only Grok was tried. Use at your own risk.

    Assistants on your machine can already reach OpenRig's MCP server locally. A cloud-hosted assistant can join a rig over MCP under a grant for its seat. Its roster entry declares "hosted": true; rig_team shows its capabilities, caveat and activity as unknown, never idle. The connection teaches it to check its inbox, claim work, return an answer or hand it on, and keep work that needs a person's approval until the answer arrives. This is experimental and unsupported. It's off by default. Nothing in OpenRig listens on the internet unless you set it up yourself. You serve rig mcp serve --http, put it behind your own TLS tunnel or proxy, and issue a token. Doing that is like opening a port in your firewall. Anyone with the URL and a valid token can act as that member within its grant. Treat the token like a password, give the member the narrowest grant, and revoke it when you're done (rig mcp token revoke <name>). We don't support, and take no responsibility for, an OpenRig reachable from the internet, just as with running OpenRig itself on the open internet. Use at your own risk. A real Grok claimed work, returned a useful note, came back in a new conversation and was refused after its grant was revoked, with its work kept. Other assistants weren't tried.

    #2095, #2127Link

  • AddedList the conversations a node could resume, and resume the exact Claude Code or Codex history a person reviewed, with no substitutes.

    Resume the exact Claude Code or Codex conversation you choose. rig seat history --rig <id> --node-id <id> lists the Claude and Codex conversations that exact node could resume. A client can then resume the history a person reviewed. It refuses rather than substitute another conversation or start fresh. Resuming a reviewed history has no CLI yet. It works only through the daemon's startup review, for clients. With Codex 0.164 on a low-effort model, the resumed conversation didn't recall an earlier fact, and the same happened outside OpenRig. This completes the three stages agreed in #1837.

    #2100, #2109 · thanks @bradvinLink

  • AddedNewer MCP clients can use the same server as existing clients.

    Clients on MCP protocol revision 2026-07-28, which has no initialize handshake, now work with rig mcp serve over stdio or --http. Existing 2025 clients still work on the same endpoint. A 2026-07-28 client (SDK 2.x) was shown working at installed scope. Serving over --http from the internet is experimental, unsupported and off by default. Anyone with the URL and a valid token can act within its grant. Give the narrowest grant, revoke it when you're done, and use it at your own risk.

    #2112Link

  • AddedOpen a terminal view of the agents working on a task on this machine.

    rig terminal open and the daemon's terminal preview accept qitem:<id> as a read-only membership view. It names stopped, missing and external owners. It doesn't follow a task as it moves, keep a reusable viewer or grant input. An explicit open still has the provider's usual workspace effects.

    #2131Link

  • FixedWork waiting on a person keeps its question and resolves from a later reply.

    Parks on a registered person's own address resolve only from a Slack reply written after the question. They keep their summary and evidence and show in NEEDS YOU.

    #2106, #2107, #2108Link

Before you upgrade 1

  • ChangedAfter installing 0.7.4, restart the daemon. The plugin refresh keeps backups, and a Codex seat running through the upgrade needs a restart.

    Install with npm install -g @openrig/cli@0.7.4, then run rig daemon stop && rig daemon start. On first start, a database update adds a column recording which grant's caller acted. Startup refreshes openrig-core 0.1.21: the queue-handoff skill and Claude hooks changed. It first copies replaced files under $OPENRIG_HOME/backups/managed-refresh/; reapply any edits from the copy. Claude seats get the new rate-limit hook at their next launch, resume, restore or handover. If a Codex seat stops at "Hooks need review", review the hooks in Codex. A Codex seat running through the upgrade warns "Hook failed … plugin contents changed; hook approval required", and some OpenRig hooks stop running in it. Codex 0.164's /permissions menu has no hook item. Preview with --plan, then restart the seat on its own conversation with rig seat restart <seat> --keep-conversation --reason "<why>": the warning goes away and OpenRig's hooks run again. This was tested on Linux with Codex 0.164; seats started after the upgrade aren't affected. Going back to 0.7.3 leaves the new column in place, unread.

    Link

Also in this release 6

Assistants as team members (experimental) 2

  • AddedExperimental hosted members can declare a webhook and show their last call.

    A hosted member's roster entry can declare a webhook trigger using secret names only. OpenRig sends a pointer to the work when it lands. A 2xx response means the endpoint accepted the ring, not that the member woke. If it doesn't claim the work in time, its person is told. rig_team and rig roster show show the member's last MCP call; rig_team also shows its latest ring. No webhook consumer was shown waking from a ring. An ordinary chat app cannot receive unsolicited events, so without a webhook-capable runner the assistant sees work only when it checks. Hosted members and internet-facing MCP are experimental, unsupported, off by default and used at your own risk. Only Grok was tried.

    #2115, #2121Link

  • ChangedWhen a member cannot be woken, its person is told.

    When work waits for a member nothing can wake, OpenRig tells its person on Steering, the TUI's Feed and Slack. The notice goes to the person, not the member. For hosted members, this notice wasn't shown with a registered person. Hosted members and internet-facing MCP are experimental, unsupported, off by default and used at your own risk. Only Grok was tried.

    #2110Link

MCP 1

  • ExpandedRemote MCP is experimental, unsupported and off by default. Use at your own risk.

    Rows record whose grant acted: attribution, not authentication. A caller's seat that was created but never launched is served instead of refused. A caller granted through a grant service hands work to its granted team, never to a caller seat, and cannot attach tags that hide text from a person asked about it. For advanced remote setups, rig mcp serve --http --grant-service <url> checks each request's key with an external grant service, with nothing cached. --oauth-resource and --oauth-issuer add OAuth protected-resource discovery (RFC 9728) and standard sign-in challenges; the key and grant still decide what a caller may do. This is experimental and unsupported. It's off by default. Nothing in OpenRig listens on the internet unless you set it up yourself. You serve rig mcp serve --http, put it behind your own TLS tunnel or proxy, and issue a token. Doing that is like opening a port in your firewall. Anyone with the URL and a valid token can act as that member within its grant. Treat the token like a password, give the member the narrowest grant, and revoke it when you're done (rig mcp token revoke <name>). We don't support, and take no responsibility for, an OpenRig reachable from the internet, just as with running OpenRig itself on the open internet. Use at your own risk.

    #2096, #2141, #2135, #2098, #2125, #2132, #2126Link

Also 2

  • FixedRate-limited Claude seats are recognised, handovers report delivery accurately, and resume sources survive snapshots.

    A Claude seat stopped by a rate limit is recognised from Claude's StopFailure hook, and a delayed older hook no longer replaces a seat's current state (#1908, #2113). A fresh Claude handover reports delivery only once the packet is submitted (#1863). Periodic snapshots keep a down agent's resume source (#2123). A resumed Pi seat no longer prints Entry not found on every restart (#2122).

    #1908, #2113, #1863, #2123, #2122Link

  • FixedThe TUI no longer crashes in a zero-size terminal and lists rigs by name; smaller fixes to reviews and identity lookup.

    The TUI starts in a terminal that reports 0 rows or columns (#2099) and lists rigs by name (#2134). The reviews count only open rows as held (#2136). Identity lookup no longer prints tmux errors (#2103). The packaged CHANGELOG.md lists every change.

    #2099, #2134, #2136, #2103Link

The kernel at daemon start 1

  • FixedA kernel already down before daemon start stays down.

    Startup brings back a kernel only when this start found it down, which is what a reboot leaves. A kernel already down before the start stays down. rig start and rig daemon start --wait-for-kernel explain why and show rig up kernel --existing as the way back. The wait-for-kernel command still exits 1 for a deliberately skipped kernel, but no longer reports a timeout and an authentication fix. This fixes 0.7.3's known issue of a long-gone kernel returning. Restore evidence lasts one daemon process: if the first daemon after a reboot exits before restore starts a seat, the next start leaves the kernel down and says so.

    #2146, #2152, #2156Link

Known issues: 16 for this release. Read them
  • A webhook ring proves only that the endpoint accepted it. An ordinary chat app can't receive unsolicited events, so a hosted assistant without a webhook-capable runner sees work only when it checks.
  • The task view is membership only. It doesn't follow a task, keep a reusable viewer or grant input, and an explicit open still has the provider's usual workspace effects.
  • Resuming a reviewed history has no CLI yet; it's through the daemon's startup review, for clients.
  • The kernel's restore evidence lasts one daemon process. If the first daemon after a reboot exits before the kernel's restore starts a seat, the next start leaves the kernel down and says so; run rig up kernel --existing.
  • An exported team isn't registry-ready by itself. rig export doesn't write a README, and openrig.dev/rigs' check fails until one is added and declared in rig.yaml docs. Add it, then run rig bundle check on the folder before you submit.
  • OpenClaw's interrupted local turns still aren't recovered. Capture the pane before sending; for an unattended seat, use the Gateway preset.
  • Whether processes a community harness starts outside its pane survive isn't exercised. rig down stops the pane only.
  • Hermes: the preset doesn't declare resume, and whether a seat's gateway exits once idle is unknown. Check with ps before relying on it.
  • A Codex seat's permission settings were enforced natively in 0.7.3's test with Codex 0.164.0; other versions weren't tested.
  • Upgrading doesn't restore Codex hook approvals an earlier OpenRig removed. Approve the hooks you mean to enable.
  • A session attached with rig attach --self can send, but replies to it may fail with transport_unavailable.
  • After a seat handover, check the successor if OpenRig reports its restore packet unconfirmed. The packet can be left typed but not sent in a Claude successor's prompt. In our test, the seat's next ordinary task got it consumed.
  • After the last managed session ends, an empty tmux server may remain running.
  • Slack threads and messages from before 0.7.3 keep 0.7.3's limits on reply routing and on what a person sees.
  • Shared channels are Slack only, the cmux path wasn't tried in a real cmux, and the TUI reads a remote host's rigs over HTTP only.
  • Not in this release: verified task viewers (#2133), switching a seat to an isolated account home (#2138, #2143), source evidence for resolving stuck findings (#2153), the stale-pane repair message (#2157), current launch evidence for fresh handovers (#2159), and a warning for out-of-range MCP daemon ports (#2160).

Thanks 12

Thank you to everyone whose work is in this release: @Aschenbath, @Nikhi00718, @bradvin, @dajiaohuang and @seanmcn, and, for reports and reviews, @pr0xc3nt4ur1 (#1822), @duncanleung (#2130), @ziadeh (#2129), @alperta (#99), @AdamWhitehurst (#1544), @smota (discussion #2117) and @oSquashBlossomo.

Verification limits
  • A real person's own Grok joined a 0.7.4 team over MCP under a revocable grant. It claimed a task, closed it with a useful note, came back to the same task, reported what it couldn't reach and when it can't be woken, and was refused after its grant was revoked, with its earlier result kept. The person drove Grok in its own app; other assistants weren't tried.
  • No webhook consumer was shown waking from a ring.
  • The notice to a hosted member's person when nothing can wake it wasn't shown with a registered person.
  • Resuming the exact conversation was shown on Claude Code and on Codex. With Codex 0.164 on a low-effort model, the resumed conversation didn't recall an earlier fact, and the same happened outside OpenRig.
  • An MCP 2026-07-28 client (SDK 2.x) was shown at installed scope.
OpenRig 0.7.3In OpenRig 0.7.3, the people you work with reach your agent teams through one gateway.11 added7 changed4 fixed

17 people thanked · Release notes

Highlights

  • AddedRegister more than one person and choose a default, who gets the last escalation step, the notice digest and workflow fallbacks.

    Register more than one person (rig gateway human add) and choose the default (rig gateway default <id>), who receives the last escalation step, the notice digest and workflow fallbacks.

    #1992Link

  • AddedA Slack shared channel joins as one participant: anyone writing there reaches your team, and each task names the channel, the sender and the policy.

    rig gateway channel add <id> --binding slack:… registers a Slack shared channel as one participant. Anyone writing there reaches the team, and each row names the channel, the sender and the policy. A channel's messages never answer or close an ask.

    #1992, #1998, #2068Link

  • AddedOrganizations and groups can carry a policy your agents can read, and rig gateway participants shows where it came from. It informs their judgment; nothing enforces it.

    rig gateway org set and group set give organizations and groups a readable policy, and rig gateway participants shows it with its source. It's context for your agents' judgment; nothing enforces it.

    #1992Link

  • Addedrig seat set-permissions <seat> --codex-permissions <file> gives a Codex seat its own sandbox and approval settings on every managed launch.

    rig seat set-permissions <seat> --codex-permissions <file> gives a Codex seat its own sandbox and approval settings, passed on every managed launch.

    #2048Link

  • AddedCommunity harness authors get a written contract: what a harness gets from OpenRig, how to write one, and how promotion is judged.

    docs/reference/community-harness-presets.md is the contract: what a harness gets from OpenRig and what it doesn't, how to write one, and how promotion is judged. Tests cover it.

    #2078, #2088Link

Before you upgrade 4

  • ChangedAfter installing 0.7.3, restart the daemon: one database update applies on its first start, and OpenRig's own plugin is refreshed with a copy kept of each file it replaces.

    Restart the daemon after installing: run npm install -g @openrig/cli@0.7.3, then rig daemon stop && rig daemon start. One database update applies on the daemon's first start. Startup refreshes OpenRig's own plugin (openrig-core 0.1.20; the messaging-the-human skill changed), first copying any file it replaces under $OPENRIG_HOME/backups/managed-refresh/. If you edited one, reapply your change from the copy.

    Link

  • ChangedIf you register a second person, choose a default with rig gateway default <id>. Until you do, the last escalation step and the notice digest wait.

    If you register a second person, choose a default: rig gateway default <id>. Until you do, the last escalation step and the notice digest wait.

    Link

  • ChangedIf a seat relied on the daemon's own environment, such as ANTHROPIC_BASE_URL, declare it in the rig's or member's env:.

    If a seat relied on the daemon's own environment (ANTHROPIC_BASE_URL, OPENAI_BASE_URL, CLAUDE_CODE_USE_BEDROCK), declare it in the rig's or member's env:. The first seat on a new tmux server now gets the same scoped environment as every other seat.

    #2047Link

  • ChangedGoing back to 0.7.2 keeps every registered person, but not the default person, shared channels, organizations, groups or policy, and it ignores a Codex seat's own permission settings.

    Going back to 0.7.2 keeps every registered person, but not the default person, shared channels, organizations, groups or policy. It keeps a Codex seat's permission settings without reading them, so its launches of that seat can be broader.

    Link

Also in this release 13

Seats & restore 1

  • FixedAn OpenClaw seat whose last local turn was refused shows as needing attention, rig down names community harness seats whose processes may outlive their pane, and a Hermes gateway runs per seat.

    An OpenClaw seat whose last local turn was refused shows as needing attention, rig down names community harness seats whose processes may outlive their pane, and a Hermes gateway runs per seat with the example launcher.

    #2092, #2077, #2097Link

Queue & messaging 1

  • ChangedA registered person can't settle an ask that was asked of someone else; from the TUI, the primary user can.

    A registered person can't settle an ask that was asked of someone else (answer_not_recorded); from the TUI, the primary user can.

    Link

Claude 1

  • ChangedA send to a Claude seat at its "Resume session" picker is refused with target_needs_input.

    A send to a Claude seat at its "Resume session" picker refuses with target_needs_input.

    Link

Codex 2

  • Addedrig seat set-permissions <seat> --codex-profile <name> picks which Codex configuration profile a seat uses on its future managed launches. Requested by @bpamiri.

    rig seat set-permissions <seat> --codex-profile <name> selects that seat's Codex configuration profile for future managed launches. Requested in #1534 by @bpamiri.

    #2048 · reported by @bpamiriLink

  • FixedCodex's own trust and config edits survive OpenRig's next launch, a duplicate trust table no longer stops Codex starting, and a seat started under a launcher gets its generation record. A community contribution.

    Codex's own trust and config edits survive OpenRig's next launch, and a single-quoted trust table no longer gains a duplicate that stopped Codex starting. Resume handles a path with a space, and a seat started under a launcher gets its generation record.

    #2034, #2035, #2046, #2038, #2084 · thanks @AschenbathLink

Slack 2

  • Addedrig slack post-open-asks posts the asks still open, and the reply hint on a person's message now answers in their Slack thread.

    rig slack post-open-asks posts the asks still open, and the reply hint on a person's message now answers in their Slack thread.

    #2086, #2055Link

  • FixedWhen an agent sets its question aside to wait on the person it asked, a colleague's reply in that Slack thread goes to the agent.

    When an agent parks its own ask on the person it asked, a colleague's reply in that thread goes to the agent. Incoming Slack messages are not automatically reposted to Slack as new asks; an agent can still deliberately ask a follow-up.

    #2119Link

TUI 2

  • AddedThe Feed's whose filter chooses whose queue you see, and settling someone else's ask from the TUI is recorded as the primary user's, with the person asked kept.

    The Feed's whose <person|all|default> chooses whose queue you see. Settling someone else's ask from the TUI is recorded as the primary user's, keeping the person asked: attribution on a trusted network, not a login.

    #2006, #2061Link

  • AddedThe TUI opens views in cmux when it runs inside cmux, and keeps a registered remote host in its tree.

    The TUI opens views in cmux when it runs inside cmux, and keeps a registered remote host in its tree on every tab.

    #2080, #2052Link

CLI & hosts 4

  • Addedrig capture --readable reads a small seat at a readable size, then gives its window back.

    rig capture --readable reads a small seat at a readable size and gives its window back, and a window gets its own size back after the web terminal.

    #2075, #2065Link

  • Addedrig doctor checks that tmux can capture a pane, and new seats keep Claude's Shift+Enter.

    rig doctor checks that tmux can capture a pane, and new seats keep tmux's TERM_PROGRAM for Claude's Shift+Enter.

    #2081, #2043Link

  • Changedrig scope --workspace <path> mission create refuses a path that doesn't exist.

    rig scope --workspace <path> mission create refuses a path that doesn't exist.

    Link

  • FixedSmaller fixes: long --wait-for-idle waits work, a dropped local send reads unconfirmed, rig export keeps pod startup files, and the delivery digest says why it sent nothing. A community contribution.

    Also: --wait-for-idle over 300 seconds works; a dropped local send reads unconfirmed; saved seat settings can target a node id; rig export keeps pod startup files; rig scope --workspace creates the first mission there; the delivery digest says why it sent nothing.

    #2020, #2024, #2060, #2051, #2087, #1093, #2063, #2066 · thanks @bradvin, @Aschenbath, @Coder8124Link

Known issues: 13 for this release. Read them
  • OpenClaw's interrupted local turns aren't recovered. The seat shows as needing attention; capture its pane before sending, since a send submits a new turn. For an unattended seat, use the Gateway preset.
  • Whether processes a community harness starts outside its pane survive isn't exercised. rig down stops the pane only; check the harness's own processes afterwards.
  • Hermes: the preset doesn't declare resume, and whether a seat's gateway exits once idle is unknown. The presets doc says it exits; check with ps before relying on it.
  • rig or rig tui started in a terminal that reports 0 rows or columns crashes on its first frame, as in 0.7.2. Start it in a terminal with a size. The fix (#2099) is on main for the next release.
  • A Codex seat's permission settings were enforced natively in our test with Codex 0.164.0, including after a managed restore and a restart. Other Codex versions weren't tested, and an older OpenRig ignores the settings.
  • Upgrading does not automatically restore missing Codex hook approvals. Earlier OpenRig versions could remove them while refreshing the managed hook block; 0.7.3 fixes that preservation bug (#2035). If Codex asks for hook review, review and approve the hooks you intend to enable. Later upgrades may ask again when the previous approval cannot be recognized.
  • A kernel whose terminals went away long ago can come back when the daemon starts. Startup restores a kernel whose seats were all left detached, which is what a reboot leaves, but it can't tell how long ago that was. A kernel gone for weeks can return from an old snapshot, including on the restart in "Before you upgrade", and offer to resume its old conversations. If you didn't expect it, decline those prompts and run rig down kernel; a kernel stopped that way stays down on later starts. rig daemon start --no-kernel skips kernel startup entirely. A fix is planned for a later release.
  • After the last managed session ends, an empty tmux server may remain running. This does not by itself mean an agent is still running.
  • Threads already affected by the parked-ask routing bug still send replies to the person asked, on their Steering, rather than to the agent. These incoming replies are no longer automatically echoed to Slack.
  • Slack messages received before this upgrade may still show OpenRig's routing footer, shared-channel policy text and attachment paths when an agent later asks a person about them. A handoff that changes the task text or replaces its Slack-origin tags also shows the text in full to avoid deleting the sender's words. Newly received messages with their original text and tags omit this generated routing, policy and attachment context.
  • Shared channels are Slack only.
  • The community harness field keeps its name (communityHarness) and its original database update; renaming them would break a return to 0.7.2.
  • The cmux path wasn't tried in a real cmux, and the TUI reads a remote host's rigs over HTTP only.

Thanks 17

Thank you to everyone whose work is in this release: @Aschenbath, @Coder8124, @bradvin, @sn1thy and @DeryFerd, and, for reports and diagnoses, @AdamWhitehurst (#2041, #2049, #2057), @borfast (#2029, #17), @jimallen (#17), @R14014 (#1069), @kainne44 (#70), @VltrnOne (#1653), @d3fvxl (#800), @fsafey (#1799), @MichelMabinuola (#980), @rakoort (#1679), @bpamiri (#1534) and @george661 (#1710).

Verification limits
  • The required five-measure performance comparison against 0.7.2 was not completed. One non-gating workload was slightly slower; it establishes neither a performance pass nor a regression. Publication proceeds with an explicit exception for 0.7.3, not a waiver for future releases.
  • Slack button interactions were not verified: the test clicks did not reach the receiving socket.
  • Registry sharing was not verified end to end. The maintainer round trip did not run, and the stranger check stopped at GitHub's first-time-contributor workflow-approval gate.
  • The Claude first-use check used a token rather than interactive sign-in; the Codex journey included assistance.
  • Some stored-copy attachment, cross-host terminal and isolation paths remain unverified. Kernel duplication, whole-database or native-session downgrade, and Windows were not exercised. Keeping already-running Codex seats through a daemon-only upgrade was not demonstrated natively.
OpenRig 0.7.2Switch a live agent between Claude Code and Codex without losing its work, and give each agent its own account.12 added2 expanded20 changed39 fixed

29 people thanked · Release notes

Highlights

  • Addedrig seat set-runtime <seat> --runtime claude-code|codex moves a live seat between Codex and Claude Code, keeping its address, its queued tasks and its claims. A community contribution.

    rig seat set-runtime <seat> --runtime claude-code|codex --reason "<why>" moves a live seat between Codex and Claude Code. The successor starts first, gets a handover and confirms it before the old runtime stops, and the seat keeps its address, queue rows and claims. --dry-run shows the settings, what is cleared and the costs; --recover finishes an interrupted switch. Built on @Aschenbath's design in #1214.

    #1895 · thanks @AschenbathLink

  • AddedA seat can run on its own Claude or Codex login: sign in to a separate home once, then name it in the seat's env:.

    A seat can run on its own Claude or Codex login. Sign in to a separate home once, natively, then name it as an absolute CLAUDE_CONFIG_DIR or CODEX_HOME in the member's or rig's env:. It applies at the seat's next launch, and rig seat status and rig provider status show which home a seat uses and where it comes from.

    #1937, #1945Link

  • AddedClaude members that share a project folder can keep their own tool rules, in the spec or with rig seat set-permissions <seat> --rules <file.json>.

    Claude tool rules per member. Claude members that share a project folder can keep their own tool rules: claude_permissions with allow and deny lists in the spec, or rig seat set-permissions <seat> --rules <file.json> --reason "<why>" for an existing seat. A change is audited and applies at the next managed launch or resume; OpenRig never writes the rules into the project's Claude settings. Checked natively on Claude Code 2.1.309: two seats in one folder enforce their own rules, a managed policy wins, and fresh, resume and fork launches enforce them. See Known issues for what isn't claimed.

    #1914Link

  • FixedA working Claude seat that quotes approval-prompt text in its own output no longer has sends and wakes refused. Real dialogs still refuse.

    A working Claude seat that quotes approval-prompt text in its own output, such as › 1. Yes, proceed (y), no longer has sends and queue wakes refused as if it were at a prompt, including when Claude draws its input box high in a tall pane. Real permission, question and MCP dialogs still refuse.

    #1955, #2005Link

  • FixedA Codex seat on the default sandbox can still commit after a resume, fork or restore, and keeps its LEARNED.md.

    A Codex seat on the default workspace-write sandbox can still commit after a resume, fork or restore, and can write its own topology folder, so it keeps its LEARNED.md. When the sandbox refuses its recap, the daemon saves it.

    #2000, #2023, #2018, #2008Link

Before you upgrade 5

  • ChangedAfter installing 0.7.2, restart the daemon: six database updates apply on its first start.

    Restart the daemon after installing. Six database updates apply on its first start: run npm install -g @openrig/cli@0.7.2, then rig daemon stop && rig daemon start.

    Link

  • ChangedOn its first start, 0.7.2 replaces OpenRig's own plugin and skill files and keeps a copy of each one. If you edited one, reapply your change from the copy.

    Startup replaces OpenRig's own plugin and skill files (openrig-core goes from 0.1.18 to 0.1.19; the delegating-work and openrig-user skills changed). As in 0.7.1, it first copies each file it replaces under $OPENRIG_HOME/backups/managed-refresh/ and logs where, edited or not. If you did edit one, reapply your change from the copy.

    Link

  • ChangedOn Linux, if a seat's tools use the session bus, set the bus address in the rig's or member's env:.

    On Linux, if a seat's tools use the session bus, set the bus address in the rig's or member's env:. Seats now start with an address that can't connect, even when a shell startup file sets XDG_RUNTIME_DIR (see Behaviour that changed and Known issues).

    #2036Link

  • ChangedName a seat's own CLAUDE_CONFIG_DIR or CODEX_HOME in the rig spec's env:. A one-off rig up --env no longer applies them.

    Declare a seat's own CLAUDE_CONFIG_DIR or CODEX_HOME in the rig spec's env:. A one-off rig up --env no longer applies those two, and says so.

    #1945Link

  • ChangedIf you might go back to an earlier version, set equivalent native Claude rules first: older code leaves per-member Claude tool rules out of launch.

    If you might go back to an earlier version, set equivalent native Claude rules first. Code from before #1914 opens the upgraded database but leaves per-member Claude tool rules out of launch, so a seat's denies stop applying. docs/reference/rig-spec.md has the details.

    #1914Link

Also in this release 63

Seats & restore 10

  • AddedAfter a person declines a Claude permission prompt, rig seat clear-attention <seat> clears it, and the send refusal says so.

    After a person declines a Claude permission prompt, rig seat clear-attention <seat> --reason "<what you saw>" clears the prompt the latest hook still names, and the send refusal says to.

    #1912Link

  • Addedrig launch <rig> <seat> first-starts one seat of a team imported with --materialize-only.

    rig launch <rig> <seat> first-starts one seat of a team imported with --materialize-only, without restoring the others.

    #1965Link

  • ChangedOn Linux, seats get the daemon's runtime directory with a session bus address that can't connect, unless a seat sets its own.

    On Linux, a seat launched by OpenRig now gets the daemon's XDG_RUNTIME_DIR, with DBUS_SESSION_BUS_ADDRESS=disabled:, a session bus address that can't connect. Tools whose sockets live in the runtime directory work in seats without per-tool setup, and a seat's D-Bus clients don't find or start the session bus on their own. A seat's own XDG_RUNTIME_DIR, from env: for example, leaves both as before, and its own bus address is kept. Unchanged: macOS, a daemon started without XDG_RUNTIME_DIR, and terminal.inherit_tmux_environment on. See Known issues.

    #2036 · reported by @borfastLink

  • ChangedIn a Pi seat OpenRig runs, an extension /command typed mid-turn runs at once instead of being refused.

    In a Pi seat that OpenRig runs, an extension /command typed mid-turn runs at once instead of being refused as a steer.

    #1943Link

  • FixedA pod seat that never launched starts fresh from its saved recipe after a daemon restart, instead of waiting at a shell. A community contribution.

    A pod seat that never launched starts fresh from its saved launch recipe after a daemon restart, instead of waiting at a shell.

    #1503 · thanks @Vaishnavi220506Link

  • FixedAfter a team's tmux server dies, rig down settles its seats, so rig archive and rig up can go ahead.

    After a team's tmux server dies, rig down settles its seats, so rig archive and rig up can proceed.

    #1999Link

  • FixedA team of terminal seats reads fully restored after rig start, and rig down names the terminals it stops.

    A team of terminal seats reads fully restored after rig start, and rig down names the terminals it stops.

    #1984Link

  • FixedA launch whose tmux made no session fails clearly instead of reading as launched.

    A launch whose tmux made no session fails as session_not_created or session_unconfirmed instead of reading launched.

    #1910Link

  • FixedA seat held at a choice prompt no hook announces, such as Claude's usage-limit dialog, now escalates while it holds work.

    A seat held at a choice prompt that no hook announces, such as Claude's usage-limit dialog, now escalates while it holds work.

    #1919Link

  • FixedA Pi or OMP seat's second startup block reaches the running turn instead of raising an error.

    A Pi or OMP seat's second startup block reaches the running turn instead of raising runtime_error.

    #1943 · reported by @astral-fleet-sessionsLink

Queue & messaging 18

  • Addedrig stream act <id> records what a reader did about a stream item, and rig stream show lists it.

    rig stream act <id> records what a reader did about a stream item: --work <row>, --decline "<reason>" or --duplicate <id>. rig stream show lists each reader's current action.

    #1899Link

  • Changedrig send to a Codex seat mid-turn says the message joins the running turn, and names --wait-for-idle for separate work.

    rig send to a mid-turn Codex seat says the message joins the running turn and may redirect it, and names --wait-for-idle for separate work.

    #2007Link

  • ChangedA rig send to a seat switching runtime is held, not typed; send it again after the switch.

    A rig send to a seat that is switching runtime is held, not typed (outcome: retained, reason: runtime_switch_in_progress); send it again after the switch.

    #1895Link

  • ChangedA task OpenRig creates itself wakes its seat from OpenRig's own sender, and a task the stuck sweep closes is recorded as closed by stuck-sweep@system. A community contribution.

    A row OpenRig creates itself, such as a stuck-sweep finding or a workflow escalation, wakes its seat from OpenRig's own sender with no reply line, instead of from the row's creator. A stuck-sweep closure is recorded as stuck-sweep@system.

    #1905, #1811 · thanks @AschenbathLink

  • ChangedWith agents.operator_session set, a dead seat's finding goes to that agent first, then the operator seat.

    With agents.operator_session set, a dead seat's finding goes to that agent first, then the operator seat (workspace.operator_seat_name), then the row's creator. Approvals still reach the person. With it unset, routing is as before.

    #2021Link

  • ChangedAn alert for a seat at a choice prompt follows queue.wake_human_rung, and only one reaches a person at a time.

    An alert for a seat at a choice prompt follows queue.wake_human_rung: under explicit-only it stays with the operator seat as a visible row, unless that seat is a person. Only one choice-prompt alert reaches a person at a time on a machine; the others wait as visible rows and post when it retires. Permission-prompt alerts post as before.

    #1919Link

  • ChangedCross-host queue writes wait 15 seconds, and a timeout gives the ID to reconcile by.

    Cross-host queue writes wait 15 seconds for the daemon's answer, and a timeout reads "queue request got no answer in time" with the ID to reconcile by.

    #1911Link

  • FixedA draft in a Claude seat's input box that starts with a blank line no longer reads as empty, so a send isn't typed into it.

    A draft in a Claude seat's input box that starts with a blank line no longer reads as an empty box, so a send isn't typed into it.

    #1977Link

  • FixedA draft-aware send to a Claude seat keeps its paste when Claude's footer changes to a hint such as "paste again to expand".

    A draft-aware send to a Claude seat keeps ownership of its paste when Claude's footer changes to a hint such as "paste again to expand" (see Known issues for #14).

    #1921Link

  • FixedA send to a Pi seat at a confirmation, input or editor dialog is refused and types nothing, instead of choosing the highlighted answer.

    An ordinary rig send to an adopted Pi window waiting at a confirmation dialog is refused with target_needs_input and types nothing, instead of choosing the highlighted answer (#2015). A later change extends that recognition to Pi's input and editor dialogs, including help rows that wrap in an 80-column pane (#2026). A Pi seat that OpenRig runs shows an extension dialog in its pane, cancels it and marks the seat as needing attention (#1996).

    #2015, #2026, #1996Link

  • FixedA queue wake refused at an approval prompt is tried once more when the seat's attention clears.

    A queue wake refused at an approval prompt is retried once when the seat's attention clears, instead of waiting for the stuck sweep.

    #1961Link

  • FixedA seat with an unrelated pane beside its own still gets sends and wakes in its own pane. A community contribution.

    A seat with an unrelated pane beside its own still gets sends and wakes, in its recorded pane.

    #1616 · thanks @Vaishnavi220506Link

  • Fixedrig queue resolve <qitemId> --decision "<evidence>" also releases a task held until a typed blocker such as external: clears. A community contribution.

    rig queue resolve <row> --decision "<evidence>" also releases a row parked on a typed blocker such as external:, fold: or auth:.

    #1809 · thanks @dajiaohuang · reported by @BillyOutlastLink

  • Fixedrig queue whoami and rig proof add find work in other catalogued projects, and rig scope mission create writes the mission's name. A community contribution.

    rig queue whoami resolves a project-tagged row against its catalogued project, rig proof add finds a slice in another catalogued project, and rig scope mission create writes the mission's name.

    #1526, #1938, #1936 · thanks @Vaishnavi220506Link

  • FixedA rig queue create whose outcome is unknown reads the task back once before reporting, and a timed-out cross-host write reads INDETERMINATE.

    A rig queue create whose outcome is unknown reads the row back once by its ID before reporting, and a cross-host write that times out reads INDETERMINATE instead of failed.

    #1978, #1911Link

  • FixedA dead seat's stuck-sweep finding goes to someone who can act, and says which rule chose them.

    A dead seat's stuck-sweep finding goes to someone who can act, not to the dead seat, and says which rule chose them.

    #2011, #2021, #2033Link

  • FixedThe reminder about work set aside to wait waits 5 minutes before reaching a seat that just started waiting.

    The parked-owner reminder no longer reaches a seat in the first 5 minutes after it starts waiting, such as just after a handoff or a question to a person. A seat at an approval or question prompt gets no grace.

    #1963Link

  • FixedA stalled-after-claim finding's age counts from the stall, not the claim.

    A stalled-after-claim finding's age counts from the stall, not the claim.

    #1959Link

Claude 3

  • AddedA Claude seat on the alias haiku with the plan permission is told that Claude Code answers its plan-mode turns with Sonnet, and how to set a full Haiku id.

    A Claude seat set to the alias haiku with the plan permission is told at launch, at restore and in rig seat status that Claude Code answers its plan-mode turns with Sonnet, and how to set a full Haiku id.

    #1942Link

  • FixedWhen Claude refuses a startup turn late, as on an expired login, OpenRig checks again before the next Enter and holds the rest.

    When Claude refuses a startup turn late, for example on an expired login, OpenRig checks again before the next startup input's Enter and holds the rest as owed.

    #1976Link

  • FixedThe model check no longer flags a Claude seat whose undated or Bedrock model id answers with its dated snapshot.

    The model-divergence monitor no longer flags a Claude seat pinned to an undated id that answers with its dated snapshot, or to a Bedrock inference-profile id.

    #1927, #1931Link

Codex 5

  • ChangedOn a Codex home with a hooks.json, OpenRig's activity hooks go there instead of config.toml.

    On a Codex home with a hooks.json, OpenRig's activity hooks go there, and its own old inline block moves out of config.toml.

    #1957Link

  • Fixedrig seat restart --keep-conversation on a Codex seat handles a path with a space, finds the resumed conversation, and says honestly when it can't prove the resume.

    rig seat restart --keep-conversation on a Codex seat keeps a writable root whose path holds a space, looks for the resumed conversation in the home the running Codex uses, and, when it can't prove the resume, says the pane restarted instead of "nothing was restarted".

    #2003, #2037, #1950, #1958Link

  • FixedWhen a Codex home has a hooks.json, OpenRig puts its activity hooks there. Your own hooks, their trust and your disables stay. A community contribution.

    When a Codex home has a hooks.json, OpenRig puts its activity hooks there and moves its own old inline block out of config.toml. Your hooks, their trust and your disables stay; @fsafey found the mixed-format problem in their fork. Inline hook trust is keyed by the managed group's actual position.

    #1957, #2028 · thanks @dajiaohuang · reported by @fsafeyLink

  • FixedA signed-out Codex seat reports login_required instead of waiting out the readiness timeout. A community contribution.

    A signed-out Codex seat at the sign-in chooser or API-key entry reports login_required instead of waiting out the readiness timeout (Codex 0.164.0 and 0.162.1).

    #1967, #1983 · thanks @AschenbathLink

Slack 2

  • ChangedEvery Slack post starts with From <seat> on <machine>, so update anything that read the sender from the last line.

    Every Slack post starts with From <seat> on <machine>, and an escalation's headline reads Waiting on <seat>: <summary>; update anything that read the sender from the last line.

    #1960Link

  • FixedSlack posts name their sender first, escalations name the seat the work waits on, and a reply from another person reaches the agent as their own message.

    Slack: every post names its sender first, an escalation names the seat the work waits on, a reply from another registered person reaches the agent as their own message instead of answering someone else's question, and Slack rows name who wrote.

    #1960, #1893Link

CLI & hosts 7

  • Addedrig capture says when a pane smaller than 80x24 may cut off a seat's prompt, with the command to resize it.

    rig capture says when a pane smaller than 80x24 may cut off the prompt a seat is at, with the command to resize it.

    #1969Link

  • ExpandedOpenRig's MCP server grows to 36 tools. A chat agent such as Claude Desktop can now pass a task it has taken on to another agent in one step, and that agent gets it as a new task. It can also hand back a task it won't finish, so the task goes back to the queue to be picked up again.

    OpenRig's MCP server adds rig_queue_handoff and rig_queue_unclaim (36 tools), so an assistant can pass held work on, or put it back, in one step.

    #1970Link

  • Changedrig up --env CLAUDE_CONFIG_DIR=… or CODEX_HOME=… isn't applied, and the CLI says so. Name a seat's home in the spec.

    rig up --env CLAUDE_CONFIG_DIR=… or CODEX_HOME=… isn't applied, and the CLI says so; other --env values work as before. Name a seat's home in the spec's env:.

    #1945Link

  • Changedrig seat status --json always carries permissions.account.advisories.

    rig seat status --json always carries permissions.account.advisories (empty unless there's an advisory).

    #1942Link

  • FixedThe ACP agents guide that rig acp run --help names now ships: rig context get reference/acp-agents.md.

    The guide that rig acp run --help names now ships: rig context get reference/acp-agents.md.

    #1930Link

  • FixedSmaller fixes from contributors: dropped input after a client disconnects, TUI health summaries and stream state, clearer kernel boot status and test docs. A community contribution.

    From contributors: queued terminal input is dropped after its client disconnects (#1636, @Vaishnavi220506); TUI focused summaries load their health findings (#1986, @Kero-66 and @Aschenbath); the TUI keeps the stream's connection state across pages (#2014, @Nikhi00718); the web dashboard reads a skipped kernel boot as "Boot not tracked", not "Unknown" (#1917, @Aschenbath, reported by @Kero-66); the compaction-and-restore scenario runs through a launch script, and the test-system docs state the CI job's real counts (#1924, #1925, @DeryFerd).

    #1636, #1986, #2014, #1917, #1924, #1925 · thanks @Vaishnavi220506, @Aschenbath, @Nikhi00718, @DeryFerd, @Kero-66Link

  • FixedClearer guidance: what setup writes to your home, how to cancel a queued task, help summaries for 14 subcommands, and all six typing-guard modes in the docs.

    Guidance: the installer guide says what setup and starting Codex seats write to your home configuration, and the operator puts project work on a team's queue; a Codex user who declines the remembered command rule is offered the operator conversation; rig queue update --help and its refusal say how to cancel a row (--state done --closure-reason canceled); rig skill audit says what its stale and hash findings mean; 14 subcommands that showed a blank help summary now have one; the openrig-user skill says a queue create's request ID isn't the row; delegating-work also applies when judging a delegated result; and docs/reference/seat-delivery.md lists all six typing-guard modes.

    #2001, #1973, #1956, #1966, #1923, #1909, #2012, #1989Link

Specs & bundles 2

  • FixedA service bundle install without Docker Compose v2 stops before it writes anything, and --plan warns that it would.

    A service bundle install on a machine without Docker Compose v2 stops with compose_missing before it writes the target or creates the team, and --plan warns that it would.

    #2025Link

  • Fixedrig export copies the team's culture file and names each seat whose agent ref points outside the export.

    rig export copies the team's culture file and names each seat whose agent ref points outside the exported folder.

    #1975Link

Context & skills 5

  • Expandedrig compact <seat> --state shows a restore that is still owed, and repeated failures open one queue item for whoever can act.

    rig compact <seat> --state and seat status show an owed restore stage and its last delivery result, and repeated failures open one queue item for whoever can act.

    #1953Link

  • FixedA managed Claude restore reads its own restore files without stopping at a Read approval, from the seat's next launch.

    A managed Claude restore reads its own restore files without stopping at a Read approval, including on macOS, through a symlinked home or project, and for the generic or configured post-compact-extra.md and preparation root. The grants apply from the seat's next launch or resume.

    #1940, #1952, #1962Link

  • FixedA restored Claude seat stopped at the resume chooser reads as waiting for a person, not as resumed.

    A seat restored with claude --resume that stops at Claude's resume chooser in a tall pane is reported as waiting for a person's choice instead of resumed, and a Codex model chooser there reads as model_selection_gate. An old chooser above a resumed session no longer reads as live.

    #2010Link

  • FixedAfter a managed compaction, a Claude seat's restore starts on the next poll instead of waiting for its screen to change.

    After a managed compaction, a Claude seat's restore starts on the next poll instead of waiting for something to change its screen.

    #1971Link

Setup & platform 11

  • Addedrig provider switch --seat <seat> moves one seat to another subscription login on the same conversation, and rig provider precheck shows what it would do.

    rig provider switch --seat <seat> now moves one seat to another subscription login on the same conversation. A Codex seat moves to a login saved in its own Codex home (--to-account <name>, Linux only), after its current login is saved as before-switch-<time>. A Claude seat moves to its own subscription token file (--token-file <path>, made with claude setup-token), and --stored-login moves it back; OpenRig keeps only the file's path and your label, never the token. rig provider precheck --seat <seat> shows what a switch would do, changing nothing.

    #1972, #1980, #1991Link

  • Addedrig provider status --refresh can read a Claude token's usage on request.

    rig provider status --refresh --provider claude --claude-token-file <path> --credential-label <label> reads a Claude token's usage on request, one model turn per refresh.

    #1901Link

  • AddedA community harness can take its first startup turn at launch. The Cursor example uses it, and OpenClaw seats keep named conversations.

    A community-harness preset can set first_input: true to hand the harness its first startup turn at launch instead of pasting it into the pane. The Cursor example uses it and is no longer startup-assisted, and OpenClaw seats keep named conversations as a local agent or a Gateway client.

    #1987, #2017, #2009Link

  • AddedRex is a terminal provider: from a Rex pane, rig terminal open <view> --window opens the team's view there. A community contribution.

    Rex is a terminal provider. From a Rex pane, rig terminal open <view> --window and the TUI open the team's view as a Rex session; --provider rex selects it.

    #1935 · thanks @vanducngLink

  • Changedrig provider switch now acts; it used to answer failed_safely every time.

    rig provider switch acts: it used to answer failed_safely every time.

    #1972, #1980Link

  • ChangedThe Cursor reference preset passes its first prompt at launch and is no longer startup-assisted.

    The Cursor reference preset is startup_assisted: false and passes its first prompt at launch.

    #2017Link

  • FixedAn open rig view keeps a seat's tile when its tmux session is replaced.

    An open rig view keeps a seat's tile when its tmux session is replaced, and a fresh replacement prints how to reopen the view.

    #1964, #1941Link

  • FixedThe daemon starts listening before it works through a backlog of queue notifications, so startup doesn't time out.

    The daemon starts listening before it works through a backlog of queue notifications, so startup doesn't time out behind them.

    #1993Link

  • FixedA database-conflict check at startup that gets no answer now says so, instead of reading as clean.

    A startup database-conflict check that can't get an answer now says so, instead of reading like a clean one.

    #1974 · reported by @calv-io-nLink

  • FixedProof-source monitoring watches the missions root, not the whole workspace.

    Proof-source monitoring watches the missions root, not the whole workspace.

    #1951Link

  • FixedQueue views, long health histories and send checks do less repeated work.

    Queue views, health reads with long histories and send checks do less repeated work.

    #2031, #2013, #1994Link

Known issues: 24 for this release. Read them
  • On Linux, seats now get the runtime directory with a session bus address that can't connect. This is an accepted trade-off, and default hygiene, not isolation. A shell startup file that sets only XDG_RUNTIME_DIR used to let a seat's clients find the session bus; now the seat keeps DBUS_SESSION_BUS_ADDRESS=disabled:. To use a session bus, set its address in the rig's or member's env:. systemctl --user reaches the person's user service manager from a seat, whatever the bus address. A Codex stdio MCP server still needs env_vars = ["XDG_RUNTIME_DIR"] in Codex's config.toml to see the variable. (#2036)
  • Per-member Claude tool rules have limits. Member denies aren't claimed to hold in bypass mode (full_bypass). Handover and restore carry the rules, but aren't proven to keep the same conversation. An allow list doesn't withdraw broader inherited grants, and these are Claude's own tool rules, not OS or credential isolation. A change applies at the next launch or resume, not in a running process. Going back to code from before #1914 drops the stored rules from launch (see Before you upgrade). (#1914)
  • Pi dialog recognition is a bounded screen check. #2015 refuses ordinary sends at an adopted Pi confirmation dialog, and #2026 later extended the same classifier to Pi's input and editor dialogs and wrapped help rows. Each was checked with a real Pi for its own case only. Layouts outside them keep the earlier behaviour, so an ordinary send can still type into them: more than six rows under a confirmation dialog's border, a widget that draws its own border, clipped or incomplete help, more than three wrapped help rows, and custom extension UIs. Neither check was repeated on the final 0.7.2 build.
  • Moving a seat's account or runtime has limits. A conversation saved under a seat's earlier home doesn't resume in its new one, and live usage refresh still reads only the daemon's own logins. A Codex login switch is Linux only; other seats on that Codex home keep their old login until their next token refresh, then stop with "signed in to another account" until you run the printed rig seat restart <peer> --keep-conversation for each. A runtime switch starts a new native conversation (only the handover carries over), clears the source runtime's model, effort and Codex profile, and doesn't apply Claude launch additions such as an agent file or run startup slash commands. Selected separate-home restart/restore and useful conversation-continuity cases passed. Runtime switching worked in both directions in a minimal setup; one direction required an extra Enter. See Verification and remaining limits below for the untested paths.
  • A new Claude agent's startup text can stay unsent in its input box. Press Enter in its terminal.
  • Claude seats on a macOS native install can read as needing attention after a restore (#86). Check the seat's terminal before acting on it.
  • A Slack channel-mapping change needs a daemon restart. Don't use rig slack disable then enable for it, which marks waiting alerts as seen.
  • Ubuntu 22.04's tmux 3.2a: the known crashing query is gone, but a narrower race remains. Prefer another tmux.
  • rig daemon start can take 20 to 40 seconds before its listener warning, longer than the TUI's 30-second "restore everything" wait. On a slow host, run rig daemon start yourself first.
  • A Claude seat signed in with a long-lived token (claude setup-token) still gets no automatic usage reading. The reader accepts only claude.ai subscription logins and reports not_subscription_login for any other. Read a token's usage on request with rig provider status --refresh --provider claude --claude-token-file <path> --credential-label <label>; the label is yours, not an account the provider confirmed.
  • Managed Claude launch requires /usr/bin/env support for -0 and -u (option support checked on GNU coreutils and macOS 15; BusyBox and older macOS unverified). Without the required option support, launch stops instead of falling back to credential-bearing command-line arguments.
  • In draft-aware mode, an agent's multi-line message to a Claude seat can remain unsubmitted when the paste changes Claude's footer hint. OpenRig withholds Enter, leaving the text in the composer and later sends waiting. Observed on Claude 2.1.309 with both 0.7.0 and the 0.7.1 pre-cut build. 0.7.2 reads Claude's recognized footer hints as part of the same composer (#1921), but the original failure didn't reproduce in a native check, so #14 remains open.
  • Prompt-looking text in a seat's recent output can still be mistaken for an active approval prompt in some layouts, so OpenRig can refuse sends and queue wakes. 0.7.2 lets sends through to a Claude seat whose running timer row sits directly above its empty, framed input box (checked natively on Claude Code 2.1.309, for the layouts exercised). An idle Claude seat with quoted prompt text above its input box, a draft in the box, a mode bar OpenRig doesn't recognize (such as ⏸ manual mode on), an unframed box, and Codex seats are unchanged. Inspect the current native prompt and the refusal before retrying; do not assume that waiting 15 seconds clears it.
  • The shared-database check needs lsof. Without a working lsof, the check can't tell whether another live daemon holds the database. The daemon now says so at startup and on /healthz, but the optional daemon.db_conflict: stop stops only on a confirmed conflict, so it doesn't stop then. The warning for a database outside OPENRIG_HOME doesn't depend on lsof. (#1974)
  • Managed Claude restoration can still ask for approvals. 0.7.2 lets a seat read its own restore files without asking, from its next launch or resume. A relative policies.claude_compaction.message_file_path still asks once, and a packet read can ask after the native conversation changes. In 0.7.1's representative test, the restore also asked to run four read-only commands, which these grants don't cover. Check the retained restore map and reported gaps before treating restoration as complete. (#1940, #1952, #1962) A native check on Claude 2.1.309 passed the Read grants with no approval prompt; a complete restore with no help isn't claimed.
  • A managed Claude restore can remain owed. If a seat stays idle after compaction, rig compact <seat> --state and seat status now show the owed stage and its last delivery result; also read its saved restore map. Before sending a manual restore request, reconcile the native conversation and pending state to avoid a duplicate; do not repeat /compact merely because the restore request has not arrived. (#1953)
  • On Linux, very large trees can still cause severe daemon stalls and file-watch-limit failures. Proof-source monitoring now recurses only at the configured missions root, so unrelated checkouts and build trees in the workspace aren't watched, but a large missions tree still is, and the stalls' cause hasn't been confirmed. (#1813, #1951)
  • A Claude startup refusal that arrives after OpenRig's last check can still race the next startup input's Enter. When OpenRig withholds Enter, the pasted input may stay in the input box: don't resend it, and follow the recovery step the seat reports. Recovery after signing in wasn't verified natively. (#1976)
  • Claude Code answers plan-mode turns with Sonnet when a seat's model is the alias haiku. That's Claude Code's own behaviour, and OpenRig now says so. Configuring the full id claude-haiku-5-5 gave a Haiku answer in a plan-mode follow-up on Claude Code 2.1.309. (#1942)
  • A cross-host queue create can still end with an unknown outcome. A timed-out rig queue create --host now reads INDETERMINATE, and the CLI reads the row back once by its ID. If it's still unknown, check that host for the original row ID before retrying. If the row exists, do not create a replacement. If a retry is needed, reuse the same --id and payload; an unsuccessful read is not proof that the row is absent. (#1911, #1978)
  • A Codex seat whose queue-state folder or team-workspace path contains a space can still be misread on an ordinary resume or restore, because those arguments come before the conversation id. An in-place restart is fixed. (#2037)
  • Automatic Codex hook approval needs OpenRig's plugin folder to match what shipped. If $OPENRIG_HOME/plugins/openrig-core holds files that didn't ship, the Codex plugin still installs or upgrades, but OpenRig approves nothing itself: an existing approval stays as it was, and Codex's own hook review applies. On a restart without a version change, if a hook file or the plugin manifest there differs from what this version shipped, OpenRig doesn't install or upgrade its Codex plugin. On a version upgrade, OpenRig's managed refresh replaces an edited plugin file with the shipped one and keeps your edited copy under $OPENRIG_HOME/backups/managed-refresh/; after upgrading, inspect those backups and reapply any deliberate customization.
  • Terminal views: a view opened before 0.7.2 needs closing and reopening to keep its tiles through a session replacement, and a replacement that takes too long can still need a reopen. This wasn't run in the Herdr, cmux or Rex apps or over SSH, so #1939 stays open. Rex wasn't run on Linux, and a Rex tile that fails 2 to 10 seconds after opening is still listed as opened. (#1964, #1935)
  • Herdr's own status for a seat can read idle or unknown while OpenRig shows it waiting (needs-input), because OpenRig doesn't feed Herdr a state. Use OpenRig's view or the Feed to find waiting seats. Reopening a view with --provider herdr adds a workspace each time; from inside Herdr, rig terminal open <view> --window reuses a matching one. (#2032)

Thanks 29

Thank you to everyone whose work is in this release: @Vaishnavi220506, @Aschenbath, @dajiaohuang, @DeryFerd, @vanducng, @Nikhila-Dhevi-R, @Nikhi00718 and @Kero-66, and, for reports, ideas and outside audit, @borfast, @BillyOutlast, @tianqizhao0704, @calv-io-n, @george661, @fsafey, @astral-fleet-sessions and the Heretek-AI team.

Thanks also to @alexveli1 and @george661, who reported #1764 (addressed by #1778 and #1944); @kainne44 and @bobbiejaxn, who reported #81 (partly addressed by #1919); @oneandonlydean, who reported #1813 (partly addressed by #1951); @todie, who reported #1419 (its closure attribution addressed by #1811); @reisalbuquerque, who reported #49 (partly addressed by #1503); @jimallen, who reported #17 (partly addressed by #2028); @parkingmeter, who reported #1933 (addressed by #1963); @vanducng, who reported #1939 (addressed by #1964 and #1941, open for confirmation); and @haichongfu and @vadym-abstract-factory, who reported #14 (worked on again in #1921; still open).

Thanks also to @reco for the runtime-switch request in #589; @pr0xc3nt4ur1 for the edge-preservation and update case in #1193; and @m3ac-AllbrittenJ and @lev-gpt for the stall-reporting and age evidence in #331.

Verification and remaining limits

This release's selected checks found no demonstrated regression against published 0.7.1 or data loss. This is not an all-paths pass. The sealed package, installed checks and a real 0.7.1 upgrade passed at their recorded scope; both first-user journeys completed.

  • Slack replies can land outside the originating thread when an agent follows the existing reply hint without --reply-to. This round trip failed in testing. The hint predates 0.7.2; the later fix #2055 is not in this release.
  • Abrupt power-loss recovery on 0.7.2 was not tested: the fixture hit its disk-growth cap before its power cut. The 0.7.1 comparison passed data and native-conversation recovery, but its separate terminal-team restore was partial. That baseline is not proof of 0.7.2 recovery.
  • Native account, home and runtime coverage is partial. Selected separate-home restart/restore and useful conversation-continuity cases passed. Runtime switching worked in both directions in a minimal setup; one direction required an extra Enter. The full home matrix, a second Claude subscription token, same-token handover and stored-home-change cases, native switch edge cases and full-kernel coverage, some Slack button cases, and the right-side agents' useful answers after resume remain untested. Controlled restart cases do not substitute for the full native matrix.
  • The named-risk managed compaction and restore exercise completed with useful continuation after about 46 minutes of work, but the adopted Claude home had no OpenRig hooks. Marker, packet and trace paths that depend on those hooks were not exercised by that run.
  • Comparable release-level speed, resource-use and provider usage/charge proof remain unavailable. No across-the-board performance improvement is claimed.

The long-paste issue #14 remains open; the Codex model-picker limitation #2010 and ordinary Codex resume/restore with a space in a workspace or queue-state path remain. The fixed in-place restart path is not proof for ordinary restore. Existing Linux session-bus, Claude member-rule, Pi recognition and other documented limits still apply.

Hermes, Cursor's plug-in work and the Codex member-permission counterpart are not included. Follow-up coverage review is scheduled for 2026-10-26 at 12:00 UTC; that is a review date, not a promise that every gap will be closed.

OpenRig 0.7.1Bring outside agents in: serve your team to apps on other machines, hand tasks to ACP agents, and start from Cursor, Hermes or OpenClaw presets.11 added5 expanded21 changed18 fixed

40 people thanked · Release notes

Highlights

  • ExpandedOpenRig's MCP server grows from 23 to 34 tools, so a chat agent such as Claude Desktop can do much more, and rig mcp serve --http serves one on another machine. A community contribution.

    OpenRig's MCP server grows from 23 to 34 tools, including identity, restore status, a rig's team and lead, following a handoff, reading a result and deciding inside a person's decision room. rig mcp serve --http serves an assistant on another machine, each caller acting as its own seat.

    #1831, #1835, #1842, #1853, #1860, #1596 · thanks @pdurlejLink

  • AddedChoose, per seat, how much automatic input reaches an agent's terminal with rig seat set-typing-guard. Input it holds stays readable and is never replayed.

    rig seat set-typing-guard <seat> --mode off|openrig-urgent|urgent-only|hold sets how much automatic input reaches a seat. rig send --urgent or an urgent queue row marks a message urgent, naming who marked it. Held input stays readable and is never replayed.

    #1770, #1781Link

  • ExpandedQuestions to you show up on the TUI's Feed. Slack still gets every ask by default, or only urgent ones if you choose.

    Asks to you. An ask lands on the TUI's Feed. Every ask still posts to Slack by default; rig gateway human set <id> slack-subscription urgent-only keeps Slack for asks marked --alert, which stand out with a mention.

    #1868, #1878Link

  • ChangedTeam skills live in each seat's own storage instead of your project, and rig skill loadout --seat <seat> shows them. A community contribution.

    Team skills live in each seat's own storage, not your project's .claude/skills or .agents/skills; rig skill loadout --seat <seat> shows them.

    #1008 · thanks @puniservLink

  • FixedA compaction OpenRig is managing picks up where it stopped after a daemon restart, such as an upgrade.

    A daemon restart, such as an upgrade, picks up a managed compaction where it stopped.

    #1866Link

Before you upgrade 6

  • ChangedAfter installing 0.7.1, restart the daemon: eight database updates apply on its first start.

    Restart the daemon after installing. Eight database updates apply on its first start: run npm install -g @openrig/cli@0.7.1, then rig daemon stop && rig daemon start.

    Link

  • ChangedOn its first start, 0.7.1 replaces OpenRig's own plugin and skill files and keeps a copy of each one. If you edited one, reapply your change from the copy.

    Startup replaces OpenRig's own plugin and skill files (openrig-core goes from 0.1.17 to 0.1.18). As in 0.7.0, it first copies each file it replaces under $OPENRIG_HOME/backups/managed-refresh/ and logs where, edited or not. If you did edit one, reapply your change from the copy.

    Link

  • ChangedClaude seats need Claude Code 2.1.280 or newer to see their team skills.

    Claude seats need Claude Code 2.1.280 or newer to see their team skills (claude --version).

    Link

  • ChangedIf an earlier version changed your worktree's Claude permission mode to acceptEdits, set it back once by hand. 0.7.1 stops changing it.

    If an earlier version reset your worktree's Claude permission mode, set it back once by hand. Launching a managed Claude seat used to rewrite defaultMode in .claude/settings.local.json to acceptEdits; 0.7.1 stops, but doesn't repair files already changed.

    #1776Link

  • ChangedIf you might go back to 0.7.0, undo any Slack subscription choice first: 0.7.0 can't read a person file that holds one.

    If you might go back to 0.7.0, undo Slack subscription choices first. 0.7.0 can't read a person file that holds one, so its people registry stops loading. Save each choice (rig gateway human show <id> --json > <id>.json), then run rig gateway human set <id> slack-subscription unset: someone on urgent-only gets every ask in Slack again, as 0.7.0 does. Set it again after you return to 0.7.1. The unset removes only the Slack subscription, so a person file that still holds a subscriptions: entry fails on 0.7.0 too. Don't restore an older gateway folder or database instead: that can lose newer people, bindings and delivery records.

    Link

  • ChangedIf you go back to 0.7.0 and then upgrade again, a seat can read as running instead of being relaunched.

    If you go back to 0.7.0 and then upgrade again, old process evidence can keep a seat reading running instead of being relaunched.

    #1906Link

Also in this release 44

Seats & restore 6

  • AddedChoose how far OpenRig and other agents may act on a seat with rig seat set-terminal-policy. Existing seats keep full control.

    rig seat set-terminal-policy <seat> --preset no-peer-interventions|help-within-instructions|full-control sets how far OpenRig and other agents may act on a seat, with exceptions for compaction and model changes. Existing seats keep full control.

    #1846Link

  • Addedrig edge add and rig edge remove change one edge on a running rig.

    rig edge add and rig edge remove change one edge on a running rig.

    #1733, #1746Link

  • ChangedA seat attached with rig attach as an outside app stays attached through rig down and restore.

    A seat joined with rig attach as an outside app stays attached through rig down and restore.

    #1827, #1834Link

  • FixedNew seats get the daemon's database and tmux folder settings.

    New seats get the daemon's OPENRIG_DB and TMUX_TMPDIR.

    #1812Link

  • FixedAfter a daemon restart that can't see the seats' tmux server, running agents are no longer detached and relaunched beside themselves.

    After a daemon restart that can't see the seats' tmux server, running agents are no longer detached and relaunched beside themselves.

    #1906Link

  • FixedA seat waiting at a prompt only its pane shows, such as a Codex approval, now shows as needing attention, with the reason.

    A seat waiting at a prompt that only its pane shows, such as a Codex approval prompt, is shown as needing attention, with its reason, in the seat view, rig ps, the compact JSON and the rig count.

    #1946Link

Queue & messaging 13

  • Addedrig watchdog update changes a job in place, and the context watch takes token or percent thresholds. A community contribution.

    rig watchdog update retunes a job in place; the context watch takes token or percent thresholds.

    #1803, #1735 · thanks @AdamWhitehurst, @akushonkamenLink

  • AddedA seat can read the observations meant for it a page at a time with rig stream subscribe and rig stream read, and rig stream show <id> says what became of one.

    rig stream subscribe <seat> and rig stream read give a seat bounded pages of the observations meant for it, and rig stream show <id> says what became of one.

    #1891, #1888Link

  • AddedOff by default: your intake seat can route stream observations one small decision at a time with rig project wake --decide, and gets back anything uncertain.

    Off by default: once decisions are enabled, rig project wake --decide lets your intake seat route stream observations with one bounded typed decision each, and hands anything uncertain back to that seat.

    #1879, #1882, #1894Link

  • ChangedStream items emitted after the upgrade are deleted after 30 days or beyond the newest 20,000, unless something refers to them. Older history is kept.

    Stream retention is on: items emitted after the upgrade are deleted after 30 days, or beyond the newest 20,000, unless a record names them (retention.stream_days, retention.stream_max_items). History from before the upgrade is kept.

    #1891, #1897Link

  • Changedrig queue show --json drops lastNudgeInputBox, and send results no longer describe the input box.

    rig queue show --json drops lastNudgeInputBox, and send results no longer describe the input box.

    #1738Link

  • ChangedAn urgent task's wake starts with "Urgent (marked by …):".

    An urgent or critical row's wake starts with Urgent (marked by …):.

    #1770Link

  • Changedrig queue show and rig queue whoami print notices for people on stderr.

    rig queue show and rig queue whoami print human notices on stderr.

    #1808Link

  • Changedrig send --dangerously-interact stops and shows you text already typed into a seat's input box instead of pasting over it.

    rig send --dangerously-interact --reason into a seat's input box stops and shows text already typed or pasted there, apart from suggestions, instead of pasting over it; clear it and retry, or pass --type-without-checking. Keys for a recognized native menu are sent as before.

    #1892Link

  • Changedrig send to a terminal seat types exactly your text, without the From and To lines, and queue wakes type nothing into it.

    rig send to a terminal seat types exactly your text, without the From/To lines, and queue wakes type nothing into it.

    #1100Link

  • ChangedA stream item over 16 KiB is stored shortened and marked, and reading after an item that was deleted says so instead of returning nothing.

    A stream body over 16 KiB is stored truncated and marked, and rig stream list --after from a pruned item returns stream_cursor_expired instead of an empty list.

    #1891Link

  • ChangedA send held because of a draft in the seat's input box reports that it wasn't delivered, and a compaction prompt held that way counts as not sent.

    A send held for a draft in the seat's input box reports inputPhase: "not_reached", and a managed compaction prompt held that way counts as not sent.

    #1884, #1889Link

  • FixedReminders and workflow keepalives survive a seat swap.

    Reminders and workflow keepalives survive a seat swap.

    #1777, #1782Link

  • FixedOne stuck task on a removed rig no longer stops the rest from being flagged, and stopped watchdog jobs let go of their schedules.

    One stuck row on a removed rig no longer stops the stuck sweep from flagging the rest, and stopped watchdog jobs release their old schedules.

    #1903, #1900Link

Claude 2

  • AddedA Claude member can bring its own agent file, system prompt, plugin folders and Advisor model. A community contribution.

    A Claude member can bring its own agent file, system prompt file, plugin folders and Advisor model.

    #1737, #1736 · thanks @AschenbathLink

  • FixedA Claude seat whose startup turn is refused reports the startup context it still owes. See Known issues for an expired login.

    A Claude seat whose startup turn is refused reports its remaining startup context as owed; with an expired login, later startup inputs can still be submitted first (see Known issues).

    #1869Link

Codex 2

  • FixedA rebuilt Codex seat keeps its narrower sandbox, and read-only Codex profiles launch. A community contribution.

    A rebuilt Codex seat keeps its narrower sandbox, and read-only Codex profiles launch.

    #1779, #1791, #1825 · thanks @bradvinLink

  • FixedUpgrading OpenRig no longer stops a working Codex seat at "Hooks need review", when its plugin is exactly what shipped.

    Upgrading OpenRig no longer stops a working Codex seat at "Hooks need review". OpenRig can renew approval of its own Codex plugin during an upgrade when the prior approval exactly matches the previous shipped bundle, nothing is disabled, and the installed bytes match the shipped bundle. Explicit disables and unrelated hooks are preserved.

    #1948Link

Slack 1

  • FixedAn answer retried from Slack or Steering after an interrupted close is used only once.

    An answer retried from Slack or Steering after an interrupted close is used once, and a replayed Slack reply stays absorbed.

    #1896, #1898Link

CLI & hosts 7

  • Addedrig acp run <qitemId> hands a task to an ACP agent such as Hermes or OpenClaw, and a new guide covers A2A agents.

    rig acp run <row> hands a row's task to an ACP agent such as Hermes or OpenClaw; a new guide covers A2A agents.

    #1823, #1829Link

  • Changedrig ps --nodes separates every column with a space and adds an ATTN column, so update scripts that read columns by position.

    rig ps --nodes separates every column with a space and adds an ATTN column before REASON; update scripts that read columns by position.

    #1780, #1876Link

  • Changedrig down asks before stopping the rig you're in, and without a terminal it stops nothing and prints the command with --yes.

    rig down asks before stopping the rig you're in; without a terminal it stops nothing and prints the --yes command.

    #1838Link

  • Changedrig up --plan no longer starts a stopped daemon; it exits with daemon_not_running.

    rig up --plan no longer starts a stopped daemon; it exits with daemon_not_running.

    #1836Link

  • Changedrig provider moves is back with a new job: filing and reading subscription move reports. It switches nothing.

    rig provider moves is back with a new job: filing and reading subscription move reports. It switches nothing.

    #1847, #1849Link

  • FixedHealth diagnoses still list when an unrelated entry has a malformed field.

    Health diagnoses still list when an unrelated diagnosis row holds a malformed field.

    #1920Link

  • FixedMany smaller fixes from contributors: faster cost history, kept drafts in the web UI, a clearer compaction plan, exports that keep culture files and more. A community contribution.

    From contributors: launch probe evidence (#1499, @Aschenbath); request IDs for creates and checked stops (#1790, #1792, @bradvin); faster cost history, ordered stream replay, kept web-UI drafts and guarded sends at Claude's MCP prompts (#1756, #1757, #1758, #1864, #1865, @Nikhi00718); a non-blocking preflight (#1759, @icey-zzz); clearer compact-plan output (#1629, @taljeri); exports keep culture files (#1657, @Totopo27); no flash in terminal views (#1663, @Vaishnavi220506); pod startup files for added seats (#1701, @AdamWhitehurst); Pi idle heartbeats (#1702, @okle100); the rig ps activity column (#1614, @shravansumanthanan); full workflow trails (#1732, @psbanka).

    #1499, #1790, #1792, #1756, #1757, #1758, #1864, #1865, #1759, #1629, #1657, #1663, #1701, #1702, #1614, #1732 · thanks @Aschenbath, @bradvin, @Nikhi00718, @icey-zzz, @taljeri, @Totopo27, @Vaishnavi220506, @AdamWhitehurst, @okle100, @shravansumanthanan, @psbankaLink

Specs & bundles 2

  • Addedrig up <spec> --name <rig> runs one spec as several rigs. A community contribution.

    rig up <spec> --name <rig> runs one spec as several rigs.

    #1692 · thanks @klueless-ioLink

  • ExpandedService bundles, off by default since 0.6.12, let a bundle bring its own services. New in 0.7.1, rig bundle install <bundle> --plan --target <folder> previews the services an install would run. Proven on Linux.

    Off by default since 0.6.12: with bundle.services_enabled on (rig config set bundle.services_enabled true), a bundle carries its Compose file, rig bundle inspect shows each service before anything runs, and rig bundle install <bundle> --target <folder> starts its services, then its seats, in that folder. In 0.7.1, --plan --target previews the services an install would run, the before-install view also names a Claude member's own agent, prompt and plugin folders, and the example secrets-manager team publishes Vault's port on the host's loopback only. Proven on Linux; not run on macOS.

    #1474, #1848, #1745, #1845Link

Context & skills 2

  • AddedA setting puts restore maps in a folder your seats are allowed to write to. A community contribution.

    policies.claude_compaction.preparation_root puts restore maps where seats may write.

    #1585 · thanks @AschenbathLink

  • FixedSeats sharing a CLAUDE.md or AGENTS.md no longer overwrite each other's role, and rig down puts your guidance files back exactly as they were.

    A seat's role no longer overwrites the others' in a shared CLAUDE.md or AGENTS.md, and rig down restores your guidance files byte for byte.

    #1840, #1854, #1859, #1867Link

Setup & platform 9

  • AddedAn optional setting stops a second daemon from using a database another daemon is already running on. By default it only warns.

    Optional daemon.db_conflict: stop keeps a second daemon off a database another live daemon holds; the default still only warns.

    #1890Link

  • Expandedrig seat status shows the permissions a seat's next launch will use and where each one comes from, and rig setup asks before adding to your shared guidance files.

    rig seat status shows the permissions a seat's next fresh launch will use and where each comes from; rig setup asks before adding OpenRig's line to your shared guidance files.

    #1843Link

  • ExpandedCommunity harnesses can report, name and reopen conversations, with examples for Cursor, Hermes and OpenClaw.

    Community harnesses can report, name and reopen conversations, with examples for Cursor, Hermes and OpenClaw.

    #1768, #1769, #1771, #1783, #1784, #1826, #1870Link

  • Changedrig setup --providers is remembered, so OpenRig starts seats only for the tools you chose.

    rig setup --providers is remembered (provider.selected), so the kernel starts seats only for the harnesses you chose.

    #1817Link

  • FixedHerdr tiles come back after a Herdr restart, you can pick a Herdr session, and the TUI's terminal button works over SSH. A community contribution.

    Herdr: tiles come back after a Herdr restart (one over SSH needs reopening), --session picks a Herdr session, and the TUI's terminal button works over SSH.

    #1796, #1076, #1748 · thanks @AschenbathLink

  • Fixedrig daemon start waits for a slow daemon instead of stopping it, and only warns when a secondary listener such as Tailscale's can't be checked. A community contribution.

    rig daemon start waits for a slow daemon instead of stopping it, and warns rather than fails when only a secondary listener, such as Tailscale's, can't be verified.

    #1716, #1743, #1793 · thanks @dajiaohuangLink

  • FixedOn Ubuntu 22.04's tmux 3.2a, closing a session no longer sends the query that crashed tmux.

    On Ubuntu 22.04's tmux 3.2a, a closing session no longer sends the query that crashes tmux.

    #1755Link

  • FixedOpenRig's hooks run even when Node isn't on the seat's PATH.

    OpenRig's hooks run without Node on the seat's PATH.

    #1727, #1728, #1729Link

  • FixedProvider credentials and the activity token no longer appear on tmux, shell or env command lines.

    Provider credentials and the activity-hook token stay off tmux, shell and env command lines; @pr0xc3nt4ur1 first raised it in #1360.

    #1907 · reported by @pr0xc3nt4ur1Link

Known issues: 22 for this release. Read them
  • A new Claude agent's startup text can stay unsent in its input box. Press Enter in its terminal.
  • Claude seats on a macOS native install can read as needing attention after a restore (#86). Check the seat's terminal before acting on it.
  • A Slack channel-mapping change needs a daemon restart. Don't use rig slack disable then enable for it, which marks waiting alerts as seen.
  • Ubuntu 22.04's tmux 3.2a: the known crashing query is gone, but a narrower race remains. Prefer another tmux.
  • rig daemon start can take 20 to 40 seconds before its listener warning, longer than the TUI's 30-second "restore everything" wait. On a slow host, run rig daemon start yourself first.
  • A Claude seat signed in with a long-lived token (claude setup-token) gets no usage reading. The reader accepts only claude.ai subscription logins and reports not_subscription_login for any other.
  • Managed Claude launch requires /usr/bin/env support for -0 and -u (option support checked on GNU coreutils and macOS 15; BusyBox and older macOS unverified). Without the required option support, launch stops instead of falling back to credential-bearing command-line arguments.
  • In draft-aware mode, an agent's multi-line message to a Claude seat can remain unsubmitted when the paste changes Claude's footer hint. OpenRig withholds Enter, leaving the text in the composer and later sends waiting. Observed on Claude 2.1.309 with both 0.7.0 and the 0.7.1 pre-cut build; #14 remains open.
  • Prompt-looking text in a seat's recent output can be mistaken for an active approval prompt, so OpenRig can refuse sends and queue wakes even while the seat is working. Inspect the current native prompt and the refusal before retrying; do not assume that waiting 15 seconds clears it.
  • rig acp run --help points to reference/acp-agents.md, which is not included in this release's reference context pack. Read daemon/docs/reference/acp-agents.md inside the installed @openrig/cli package instead.
  • The shared-database check needs lsof. #1763's warning that another live daemon is using the same database, and the optional daemon.db_conflict: stop, find that daemon with lsof. On a host without a working lsof (each lsof call times out after 1 s), the check is skipped without a message, so neither the warning nor the stop happens. The warning for a database outside OPENRIG_HOME doesn't depend on lsof.
  • Managed Claude restoration can require native approvals. On a seat without bypass permissions, restoration can ask to read OpenRig files outside its working directory. In a representative openrig-core test on Claude Code 2.1.309 (acceptEdits), the restore and audit completed after three one-time Read approvals (the restore marker, post-compaction instructions and refocusing skill) plus four approvals for read-only commands. Check the retained restore map and reported gaps before treating restoration as complete.
  • A managed Claude restore can remain owed without showing why delivery is delayed. If a seat remains idle after compaction, inspect rig compact <seat> --state and its saved restore map. Before sending a manual restore request, reconcile the native conversation and pending state to avoid a duplicate; do not repeat /compact merely because the restore request has not arrived.
  • On Linux, workspaces containing very large checkout or build trees can cause severe daemon stalls and file-watch-limit failures. The recursive proof-source watcher covers the workspace root. Keeping large checkout/build trees outside that root may reduce exposure; this mitigation has not yet been verified. (#1813)
  • A Claude startup with an expired login can still submit later startup inputs before noticing the refusal. The packaged whats-new (reference/whats-new.md) overstates the hold behavior. Resolve the login and follow the seat's reported continuation guidance; this test did not verify recovery. (#1869)
  • On Claude Code 2.1.309, a seat configured with the model alias haiku and the plan permission answered on Sonnet in one observed run. Configuring the full id claude-haiku-5-5 gave a Haiku answer in the plan-mode follow-up.
  • A Cursor seat's startup is assisted. It reports attention_required and needs one operator acknowledgement: rig seat clear-attention <seat> --reason "<why>". This wasn't rechecked natively on 0.7.1. (#1870)
  • A resumed Codex seat can be misreported as not interactive when its header has scrolled off and its footer uses a multi-word model label such as GPT-6.1 Sol medium; rig up --existing can then stop. Reported on 0.7.0; the same recognition checks remain in 0.7.1. (#1764)
  • Cross-host queue creation can report failure after the row was created. A rig queue create --host request can time out or return failure even though the destination host created the row. Check that host for the original row ID before retrying. If the row exists, do not create a replacement. If a retry is needed, reuse the same --id and payload; an unsuccessful read is not proof that the row is absent.
  • Automatic Codex hook approval needs OpenRig's plugin folder to match what shipped. If $OPENRIG_HOME/plugins/openrig-core holds files that didn't ship, the Codex plugin still installs or upgrades, but OpenRig approves nothing itself: an existing approval stays as it was, and Codex's own hook review applies. On a restart without a version change, if a hook file or the plugin manifest there differs from what this version shipped, OpenRig doesn't install or upgrade its Codex plugin. On a version upgrade, OpenRig's managed refresh replaces an edited plugin file with the shipped one and keeps your edited copy under $OPENRIG_HOME/backups/managed-refresh/; after upgrading, inspect those backups and reapply any deliberate customization.
  • With CODEX_HOME set in a seat's environment, rig seat restart --keep-conversation can report that the resume was not proven and that nothing restarted, although the process actually restarted and resumed. Inspect the seat's pane and native /status before retrying; a failed proof read is not proof that no restart occurred.
  • rig provider switch does not switch a seat's account in 0.7.1. Its precheck can refuse an unknown target, and its execution path is not yet wired. The separate home-level Codex auth-switch/restart path is not this command.

Thanks 40

Thank you to everyone whose work is in this release: @Aschenbath, @bradvin, @Nikhi00718, @AdamWhitehurst, @puniserv, @pdurlej, @klueless-io, @shravansumanthanan, @taljeri, @Totopo27, @Vaishnavi220506, @okle100, @dajiaohuang, @icey-zzz, @akushonkamen, @psbanka and @adampog, and, for reports and ideas, @lev-gpt, @XVVH, @Kero-66, @pr0xc3nt4ur1, @VltrnOne, @BillyOutlast, @gogabrielordonez, @geoff-dhango, @alexveli1, @aanestesia, @team-sudarshana, @oneandonlydean, @t1m3fr33d0m, @smota and @z4cc.

Thanks also to @george661, who reported #1710 (partly addressed by #1721); @m3ac-AllbrittenJ, who reported #331 (partly addressed by #1801); @shintaii and @gopinathrimc, who reported #27 (partly addressed by #1735); @kainne44 and @bobbiejaxn, who reported #81 (partly addressed by #1876 and #1946); and @haichongfu and @vadym-abstract-factory, who reported #14 (partly addressed by #1871).

OpenRig 0.7.0Restarting your machine brings the team back, and quiet hours hold questions until you're back.6 added16 changed8 fixed

16 people thanked · Release notes

Highlights

  • FixedAfter a reboot, the daemon brings its kernel back by itself. A community contribution.

    After a reboot, the daemon restores a kernel whose seats are all detached.

    #1081 · thanks @haralezLink

  • AddedSet quiet hours for a person: routine questions wait until they're back and arrive once. Escalations still go through.

    Quiet hours for the person. rig gateway human quiet set <id> --daily HH:MM-HH:MM (or --until) holds routine asks while the person is away and posts each one once when they're back. Escalations still go through.

    #1584, #1606, #1649, #1720Link

  • ChangedCommands like rig archive, rig snapshot, rig export and rig restore --rig now take a rig's name instead of its id, and say so when two rigs share a name. A community contribution.

    Rig names everywhere. archive, unarchive, release, shrink, expand, snapshot, export, restore --rig and the matching MCP tools take a rig's name. A name two rigs share says so.

    #1681 · thanks @Nikhi00718Link

  • FixedA rig with one seat missing a startup file still restores all the other seats.

    A seat missing a startup file no longer blocks the whole rig's restore; the other seats come back.

    #1696Link

  • FixedA busy daemon now gets your request instead of a refusal, and a write that timed out says its result is unknown.

    A busy daemon gets the real request; the CLI refuses only when it's confirmed down, and a timed-out write says its outcome is unknown.

    #1650Link

Before you upgrade 5

  • ChangedAfter installing 0.7.0, restart the daemon: six database updates apply on its first start.

    Restart the daemon after installing. Six database updates apply on its first start: run npm install -g @openrig/cli@0.7.0, then rig daemon stop && rig daemon start.

    Link

  • ChangedNew agents no longer inherit accounts or keys set in tmux's global environment. Put them in the seat's env, or turn the old behaviour back on.

    If you pass accounts or API keys to new agents through tmux's global environment (tmux set-environment -g …), new agents no longer inherit it. Put the values in the seat's env, pass rig up --env KEY=VALUE, or keep the old behaviour with rig config set terminal.inherit_tmux_environment true. rig setup warns when it sees a custom tmux configuration. Running agents aren't affected.

    Link

  • ChangedOn its first start, 0.7.0 replaces OpenRig's own plugin and skill files and keeps a copy of each one. A copy doesn't mean you changed anything.

    Startup replaces OpenRig's own plugin and skill files with 0.7.0's copies. It first copies each file it replaces under $OPENRIG_HOME/backups/managed-refresh/ and logs where, whether or not you edited it: about 22 copies on the first start after upgrading from 0.6.14, so a copy doesn't mean you changed anything. If you did edit one, your change may stop working until you reapply it from the copy; the log line names the original file.

    Link

  • ChangedIf you send tasks to another machine by its own id, run rig host doctor once for that host.

    If you write queue rows to another machine by its own id (member@rig@<self-id>), run rig host doctor <alias> once per host so the binding learns its address.

    Link

  • Changedrig provider moves is gone, so a script that calls it needs changing.

    If a script uses rig provider moves, change it: the command and its setting are gone.

    Link

Also in this release 20

Seats & restore 3

  • ChangedNew agents start from a clean environment instead of tmux's global one.

    New agents start from a clean environment, not tmux's global one.

    #1573Link

  • FixedSeats added to a running rig now get its culture and startup files, on rigs created with 0.7.0.

    Seats added to a running rig get its culture and startup files (rigs created on 0.7.0).

    #1632Link

  • Fixedrig up --env now reaches every way a seat can be launched.

    rig up --env reaches every launch shape.

    #1511Link

Queue & messaging 4

  • AddedSave modes such as "asleep" or "out of office" for a person, end them on a schedule, and see what each one changed.

    Modes for the person. rig gateway human mode saves and applies a person's modes, ends them on a schedule with --until, and reports what each one changed. Inside a mode's agreed "decision room", the agent that asked can record a delegated decision; permission prompts are never decided this way.

    #1656, #1715, #1705Link

  • Addedrig queue show --json says why a wake didn't get through. A community contribution.

    rig queue show --json says why a wake didn't land.

    #1555 · thanks @1solomonwakhunguLink

  • ChangedA task closed as done can no longer say it's blocked; block it on its follow-up instead. A community contribution.

    A done close can't use --closure-reason blocked_on; use rig queue block <id> --on <child>.

    #1704 · thanks @AschenbathLink

  • FixedWatchdog deliveries are recorded as they happened, and repeated refusals at a prompt raise an alert.

    Watchdog deliveries are recorded as they happened, and repeated refusals at a prompt raise an alert.

    #1713Link

Claude 1

  • ChangedBefore a new Claude agent's first message, OpenRig waits briefly for its input box. Delivery still isn't guaranteed; see Known issues.

    Before a new Claude agent's first startup message, OpenRig looks briefly (up to about five seconds) for Claude's input box, and keeps its checks on the submission. It doesn't guarantee delivery; see Known issues.

    A new Claude agent's startup text can stay in its input box unsent. If a fresh Claude seat sits idle with text at its prompt, open its terminal and press Enter.

    #1730Link

Codex 1

  • AddedCodex seats that use openrig-core now get its refocus and skills, and a fresh Codex seat starts without the hook review.

    Codex seats that select openrig-core get its refocus and skills: OpenRig installs the plugin into Codex and, on a first install, trusts its own six hooks after checking their files, so a fresh Codex seat starts without Codex's hook review. The file check happens only when trust is granted: a later edit to the cached hook scripts keeps that trust, as with any hook trusted in Codex. The trust covers that Codex home, so your own Codex sessions there load the plugin too; its hooks do nothing outside an OpenRig seat. A plugin or hook you already disabled, or left untrusted, keeps your choice.

    #1824Link

Slack 1

  • FixedIn Slack, a thread reply answers only a question asked before it, and a rejected message isn't posted again. A community contribution.

    Slack: a thread reply answers only a question posted before it, and a rejected message isn't re-posted.

    #1568, #1703 · thanks @AschenbathLink

TUI 2

  • AddedThe TUI's agent table shows each seat's effort setting. A community contribution.

    The TUI's agent table shows each seat's configured effort.

    #1529 · thanks @tianxingjian2406Link

  • ChangedA TUI left open says when it no longer matches the daemon's version, and refreshes less often.

    A long-open TUI says when its build differs from the daemon's, and refreshes less often.

    #1600Link

CLI & hosts 4

  • Changedrig provider moves and its setting are removed; report a subscription move as a task instead. rig slack verify drops --reason and --actor.

    rig provider moves and provider.subscription_moves are removed; report a subscription move as a queue item instead. rig slack verify lost --reason and --actor.

    #1672, #1674Link

  • Changedrig up --plan waits as long as a real launch, and rig seat restart and rig policy permissions apply now ask for permission.

    rig up --plan waits as long as an apply. rig seat restart, and policy permissions apply, now ask for permission.

    Link

  • ChangedSome output changed: rig gateway human list shows availability, rig attach prints Sender:, and a reused deliveryId no longer stops a send.

    Output shapes: rig gateway human list prints availability (available|focus|away|off); rig attach prints Sender:; a reused deliveryId no longer deduplicates a send.

    Link

  • Fixedrig ps --rig now filters correctly and says when it doesn't know a rig. A community contribution.

    rig ps --rig and --host --rig report an unknown rig and filter correctly.

    #1690, #1698, #1706 · thanks @Nikhi00718Link

Context & skills 2

  • Addedrig compact --cancel stops a compaction that's already under way, without restarting the daemon.

    rig compact --cancel stops a managed compaction that already sent /compact, with no daemon restart.

    #1660Link

  • ChangedA new agent's first message now says it's identity context, not a task, and an agent with nothing to start on waits for an assignment.

    A new agent's first startup message says it's OpenRig's identity context, not a task, and a seat with nothing else to start with is asked to confirm its identity and wait for an assignment.

    #1754Link

Setup & platform 2

  • ChangedTeam agents ask for permission less often: 15 housekeeping commands no longer prompt.

    Team agents are asked for permission less often: 15 housekeeping commands no longer prompt.

    #1665Link

  • Changedrig setup keeps 10,000 lines of tmux history, down from 50,000. A community contribution.

    rig setup keeps 10,000 rows of tmux history, down from 50,000.

    #1264 · thanks @Quentin-MLink

Known issues: 5 for this release. Read them
  • A new Claude agent's startup text can stay in its input box unsent. If a fresh Claude seat sits idle with text at its prompt, open its terminal and press Enter.
  • The TUI's terminal button refuses inside a Herdr pane reached over SSH (also in 0.6.14). Start the TUI with env -u SSH_CONNECTION -u SSH_CLIENT -u SSH_TTY rig tui, or run rig terminal open '<view>' --provider herdr. A fix is on its way.
  • Claude seats on a macOS native install can read as needing attention after a restore (#86). A fix is in progress and isn't in this release.
  • A Slack channel-mapping change needs a daemon restart (rig daemon stop && rig daemon start). Don't use rig slack disable then enable for it: enabling marks any alerts waiting to post to Slack as already seen, so open exchanges miss them.
  • Ubuntu 22.04's stock tmux 3.2a can crash its whole server when OpenRig checks a pane that has just closed, interrupting the other sessions on that server. Avoid tmux 3.2a for OpenRig; check your version with tmux -V. A replacement version has not been verified against this crash.

Thanks 16

Thank you to everyone whose work is in this release: @Nikhi00718, @Aschenbath, @PROACTIVA-US, @jayhemnani9910, @rudycelekli, @markankamaransheogarat-sys, @haralez, @tianxingjian2406, @1solomonwakhungu, @AdamWhitehurst, @Quentin-M, @arxh80, @DeryFerd, @okle100, @zichen0116 and @13pgpg.

Tested on our own machines, and with first-time setups on Claude and on Codex, before release. A first-time setup on a Mac wasn't completed.

OpenRig 0.6.140.6.14 is the last planned release of the 0.6 line: a small set of stability fixes on top of 0.6.13.3 added7 changed1 fixed

1 contributor · Release notes

Highlights

  • AddedAn agent an older OpenRig launched that stopped taking messages after an upgrade can be repaired in place, keeping its session and history.

    Agents with no recorded pane can be repaired. rig reconcile-session <seat> --repair-missing-pane --no-launch fills in only the missing pane after looking at the session twice. It keeps the seat's session, resume token and history, and adopts nothing. It refuses, changing nothing, when there's more than one pane or window, the pane changes between its two looks, a seat operation is running, or typing protection is on. If messages to an agent are refused with "Managed pane identity unavailable or changed; no input written." and that seat's pane was never recorded (seats an older OpenRig launched are often in this state), repair it in place, then send again; the repair needs typing protection off for that seat, so turn it off only if the person agrees, and back on afterwards.

    The in-place repair refuses adopted seats and ambiguous panes. For a confirmed live seat, plain rig reconcile-session <seat> --no-launch re-adopts it into a new session row and attempts to capture its resume token; conversation continuity is not verified. If the intended pane is unclear, use rig context get help.

    #1564Link

  • AddedA new getting-started page written for people: how the pieces fit, and the quick way in through the rigs skill.

    A getting-started page for people. docs/reference/quickstart.md explains how the pieces fit, the quick way in through the rigs skill, and what OpenRig changes on your machine. getting-started.md becomes the setup reference for the agent doing the setup.

    rig context get reference/quickstart.md doesn't resolve. Read the page on GitHub or in the package's docs/reference/.

    #1565Link

Also in this release 9

Queue & messaging 1

  • Changedrig ask --wake now refuses an agent it can't wake (Pi, custom or unrecorded) instead of trying a Claude wake.

    rig ask --wake refuses a runtime it can't wake (Pi, custom or unrecorded) instead of quietly trying a Claude wake. Upgrade the CLI and the daemon together to catch every case.

    #1561Link

TUI 1

  • Changedrig ps and the TUI read the list of agents through an index instead of scanning the whole event log.

    An indexed inventory read. The inventory read behind rig ps and each rig tui refresh now finds launch fences through an existing index instead of scanning the whole event log, and returns the same rows.

    #1617Link

CLI & hosts 2

  • ChangedWhen a message or a compaction is refused because an agent's terminal was never recorded, the error now names the repair command.

    The refusals name the fix. The send refusal and the compaction refusal for a seat with no recorded pane now name the repair command, and the compaction refusal explains how to turn typing protection off and on with the person's agreement. rig config --help lists the new Mac setting, rig ask --help explains its exit codes, and the CLI reference and the openrig-user skill list the repair.

    #1594Link

  • ChangedThe bundled openrig-core plugin moves to 0.1.15, and /healthz reports the daemon's user ID beside its process ID.

    The bundled openrig-core plugin goes from 0.1.14 to 0.1.15, and /healthz gains an euid field beside pid.

    Link

Context & skills 2

  • ChangedRefocus does less work on a busy machine.

    Refocus does less work on a busy machine. It finds each notes file itself instead of starting the CLI once per level.

    #1563Link

  • FixedA manual compaction keeps waiting while the agent sits at an approval, instead of giving up. OpenRig never answers the approval for you.

    A manual compaction waits through an approval. When a seat stops at an ordinary approval prompt while preparing, rig compact keeps waiting inside its deadline instead of giving up. OpenRig never answers the approval itself. A manual rig compact can take longer to answer: its preparation gets 180 seconds (was 120) and the request 240 seconds (was 180).

    After a compaction, confirm it ran by the restore request or the drop in context, and check that refocus showed the agent's current work.

    #1562Link

Setup & platform 3

  • AddedOn a Mac shared by several accounts, an optional check stops the CLI from reaching another account's daemon by accident.

    An optional Mac check, off by default. On a Mac shared by several accounts, rig config set transport.local_user_guard true makes the CLI refuse a local daemon that another account runs. It's a guard against reaching the wrong daemon by accident, not authentication.

    #1566Link

  • ChangedAfter upgrading the CLI, restart the daemon. No database change runs this time; coming from 0.6.12 or earlier, 0.6.13's runs on the first start.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. No database migration runs. Coming from 0.6.12 or earlier, read 0.6.13's notes first: its migration runs on the first start.

    Link

  • ChangedThe roadmap drops three finished items.

    The roadmap drops three finished items.

    #1560Link

Known issues: 11 for this release. Read them
  • The in-place repair refuses adopted seats and ambiguous panes. For a confirmed live seat, plain rig reconcile-session <seat> --no-launch re-adopts it into a new session row and attempts to capture its resume token; conversation continuity is not verified. If the intended pane is unclear, use rig context get help.
  • On a Mac with several user accounts, a second user's rig commands can reach the first user's daemon on the default port unless the Mac check above is on. Running each person's daemon on its own port lets both work, but doesn't keep them apart.
  • Restarting a Codex seat in place to switch its account works on Linux only. On a Mac it refuses and leaves the other seats alone.
  • A Pi seat can start on a row as soon as it's told about it, before a timed wake set for it. If timing matters, watch the row.
  • rig up <rig> --existing can refuse to restart a rig after one of its seats was stopped on purpose. Use rig restore <snapshot> --rig <rig> instead; the stopped seat stays awaiting your decision.
  • An open rig tui keeps the daemon busy, re-reading every 30 seconds, and keeps its old code after an upgrade. Quit it when you're done, and reopen it after upgrading.
  • After a compaction, confirm it ran by the restore request or the drop in context, and check that refocus showed the agent's current work.
  • A fresh in-place handover of a Claude seat can report ready early. Check that the new agent read its packet.
  • rig context get reference/quickstart.md doesn't resolve. Read the page on GitHub or in the package's docs/reference/.
  • Slack: missed replies in older open threads aren't caught up, and private channels and direct messages aren't recovered.
  • Known issues from 0.6.13 still apply.
OpenRig 0.6.13See the model each seat last reported using, give a seat its own working folder, and run a lighter daemon on Linux.5 added3 expanded17 changed20 fixed

12 contributors · Release notes

Highlights

  • AddedSee which model each agent was last seen using, beside the model it's configured for.

    See which model a seat was actually using. rig ps --nodes, rig roster show and rig roster find show the model each seat's current agent was last seen using, beside its configured model, with where and when it was read. Claude and Pi readings come from the agent's own responses; Codex's come from its recorded turn settings. Missing or stale evidence reads unknown, never the configured model. Plain rig ps --nodes prints one model line per seat after the table, and JSON gains modelObservation.

    #1493Link

  • AddedMove an existing agent to a new working folder without recreating it; its address, tasks and history stay. A community member's earlier work, finished here, after a community member's report.

    Move a seat to a new working folder: rig seat set-cwd <seat> --cwd <absolute-path> --reason <text> saves an existing seat's working folder for its next fresh launch or rebuild handover, and keeps its address, queue and history. It refuses when files already in the new folder would clash with the startup files the next launch writes. The running agent doesn't move: switch with rig seat launch <seat> --fresh --stop --reason "<why>" or a rebuild handover. rig seat status shows the saved folder.

    rig seat set-cwd checks the new folder once: a refusal can leave the folder created, and background work, such as a Claude seat's collector files or a managed compaction's restore map, can use the saved folder before you switch. Switch promptly, and don't run rig down/rig up or a fork handover first.

    #1498 · thanks @Aschenbath · reported by @d3fvxlLink

  • FixedHanding a Claude agent over in place now waits for the new Claude before typing its handover, in the common case. Reported by a community member.

    A Claude seat handed over in place waits for the new Claude. A fresh handover that reuses the old occupant's pane could read the old Claude's screen as the successor being ready, and type the handover packet into a shell before the new Claude had started. A ready result taken from that history is now checked against the current screen, so the packet waits. This corrects the common case.

    A fresh in-place handover of a Claude seat can still report ready early in some cases: a screen without a header whose process list can't be read, a Claude process seen but not proven, or a pane or screen that can't be read. Check that the successor read its packet.

    #1553 · reported by @AdamWhitehurstLink

  • ExpandedSlack now recovers missed messages in mapped channels, recent threads and channels relayed from another machine. Reported by a community member.

    Slack recovers what it missed in more places. Missed-message recovery used to read only the configured channel's top-level history, so a reply in an older thread or a message in a mapped channel was lost for good. It now also recovers the channel map's channels from when each was adopted, replies in tracked threads whose root was posted or which closed in the last seven days, and, on a machine without its own Socket Mode connection, each channel the hub has relayed to it, from that channel's first relayed event. A recovered reply lands as a late row in its thread and never answers a decision; the seat reads it and decides. A Slack rate limit now holds that method for every channel, or every thread, and is kept across a restart. rig slack status shows a line per channel and a thread line. On its first start, threads inside the seven-day window are scanned once from their root; replies that already landed are recognised and not delivered twice.

    Missed replies in older open threads aren't caught up; slack-thread-coverage.json isn't pruned yet; a default-channel backlog can drain at up to about half its earlier rate while threads also need calls; and a downgrade to an older release and back inside a rate-limit window can let other channels call Slack during that window.

    #1536 · reported by @z4ccLink

Also in this release 41

Seats & restore 3

  • ExpandedGrow a team or remove an agent by the team's name, not only its ID. A community contribution.

    rig grow <rig> and rig remove <rig> <node> accept a rig name as well as its id; a name two active rigs share is refused with the candidate ids.

    #1407 · thanks @ivanenevLink

  • FixedAfter a failed restore, a fresh launch that comes up ready clears the old warning. Reported by a community member.

    After a failed restore, a fresh launch that reports ready clears the old restore warning: rig ps and rig seat status stop showing attention_required from it, and rig seat clear-attention no longer refuses.

    #1527 · reported by @Hexgunner69Link

  • FixedAn idle Claude Code or Codex agent now reads idle even while its terminal redraws.

    A Claude Code or Codex seat showing a complete idle screen reads idle in JSON and filters even when the terminal repaints, instead of running.

    #1521Link

Queue & messaging 4

  • ChangedSeveral reminders that come due together now arrive as one message, instead of one interruption each.

    Parked rows for one seat whose wake timers fall due in the same pass now arrive as one message naming every row, instead of one interruption each. A single reminder, a custom --wake-message and repeating waits keep their own message.

    #1507Link

  • FixedA message whose sender gave up waiting is never typed later.

    A rig send --wait-for-idle whose caller went away (Ctrl-C, or its own timeout) used to keep waiting in the daemon and type once the seat went idle; if no input has started, it now types nothing, then or later, and is refused with caller_cancelled. The same holds for broadcast recipients not yet reached and for Enter-only sends.

    #1513Link

  • FixedWhen a task for a person is closed without a confirmed follow-up, the agent that closed it hears about it, not the person. A community member's earlier work, finished here, after a community member's report.

    When an agent closes an item addressed to a person and the follow-up can't be verified, the stuck-item finding goes to the agent that closed it instead of to the person.

    #1495 · thanks @Aschenbath · reported by @aanestesiaLink

  • FixedFiltering tasks by several states now works with a space after the comma. A community contribution.

    rig queue list --state "pending, in-progress" with a space after the comma now matches both states, as does the MCP rig_queue_list tool.

    #1501 · thanks @Nikhi00718Link

Claude 6

  • ChangedThe restore check can now report caveats about hooks where it used to show green. Reported by a community member.

    rig restore-check can report caveats where it used to be green. Its hook check now tells apart a saved hooks resource, the core plugin's relay, and neither, and reads a broken or unknown plugin selection as a caveat. It still exits 0.

    #1537 · reported by @bpamiriLink

  • ChangedClaude agents now get your editor and display, so Ctrl+G opens your editor and image paste can work. A community contribution.

    Managed Claude seats get your editor and display. Seats launched with a native permission mode now receive EDITOR, VISUAL, DISPLAY, XAUTHORITY and an absolute WAYLAND_DISPLAY, so Ctrl+G opens your editor and image paste can work. A running seat picks it up at its next launch (rig seat launch <seat> --fresh --stop --reason "<why>", or rig down then rig up --existing). A git commit without -m inside such a seat now opens your editor.

    #1546 · thanks @AdamWhitehurstLink

  • ChangedThe refocus work packet stays off; when you turn it on, each part of it is now kept short.

    The refocus work packet stays off for both Claude Code and Codex. With OPENRIG_REFOCUS_WORK_PACKET=1, each field is now bounded: one-line summaries of about 160 characters with a rig queue show <id> pointer, at most 20 held and 10 next rows with a count of how many are shown, and section bodies cut at about 1,500 characters. There's no total size cap.

    #1542Link

  • FixedClaude sessions with an older PATH stop showing "node: command not found" after each reply: OpenRig's hooks now call its own Node directly.

    The bundled openrig-core plugin goes from 0.1.13 to 0.1.14. The Claude activity-relay and context-collector hooks OpenRig writes into a project's .claude/settings.local.json now call the daemon's own Node by its absolute path instead of bare node, so a Claude session with an older PATH stops showing "node: command not found" after each reply. Existing bare-node entries are refreshed automatically, and your own wrappers are kept.

    The plugin's own manifest hooks still call bare node, so a Claude session with an older PATH can still show a Stop-hook error from them, and two plugin hook runs for the same seat aren't serialized.

    #1545Link

  • FixedA Claude Code approval menu for MCP servers now reads as needing you, so a message isn't pasted into it. Reported by a community member.

    Claude Code 2.1.303's MCP-server approval menu now reads as needing input, so a restore doesn't call that seat ready and an ordinary send no longer pastes into the menu.

    A fresh running hook still sends into Claude's MCP approval menu.

    #1549 · reported by @AdamWhitehurstLink

  • FixedA Claude agent started through a wrapper script now restores as ready instead of needing attention. A community contribution.

    A Claude launched through a wrapper script (a claude on PATH that execs the real binary) is now proven by its executable path, so a restored auto-mode seat whose banner has scrolled away resumes ready instead of needing attention.

    #1540 · thanks @AdamWhitehurstLink

Codex 4

  • ChangedWhen an in-place Codex restart stops at a startup screen, the report says which screen and who decides.

    When rig seat restart --keep-conversation stops at a Codex startup screen, the report names it (hook review, folder trust, model choice or update), says who decides, and points to rig capture and the recovery command.

    #1502Link

  • ChangedThe in-place restart's help says when an adopted agent refuses and which conversation a restart can prove.

    rig seat restart --keep-conversation --help says an adopted seat refuses with claimed_session and which conversation a restart can prove.

    #1509Link

  • FixedCodex's folder-trust question now reads as a question, so startup text isn't typed into it. Reported by a community member.

    Codex's current "Trust this folder?" panel reads as a folder-trust gate instead of booting or ready, so startup text and Enter don't reach it.

    #1494 · reported by @alexveli1Link

  • FixedAn old menu in a Codex agent's scrollback no longer blocks a message. Reported by a community member.

    An old numbered menu in a Codex pane's scrollback no longer blocks a send when a complete empty input box sits below the status row.

    A send to a seat can still be refused for a quoted permission prompt that isn't really waiting, outside the Codex layout this covers.

    #1548 · reported by @bpamiriLink

Pi 3

  • ChangedPi agents now use the reasoning effort set for them, and you can set or check it per agent. A community contribution.

    Pi seats now use their effort. An effort already in a spec reaches Pi as --thinking <level> from each seat's next managed launch, restore or handover, and on every managed launch and resume after that. rig seat set-effort and rig seat effort now work for Pi: the report shows what was requested, saved, sent and, on Pi 0.99.0 or later, recorded.

    #1528 · thanks @smotaLink

  • FixedAn OMP agent that hit a temporary provider error can be retried with an ordinary send. A community contribution.

    An OMP seat whose turn ended with a typed transient provider failure (status 408, 429, 500, 502, 503, 504 or 529) can take an ordinary rig send retry instead of staying in needs-input; the error stays visible in its pane, and nothing retries on its own.

    An OMP seat releases needs-input for any failure carrying one of the seven transient statuses, including an authentication failure that carries one; untyped errors and Pi seats keep attention.

    #1550 · thanks @1solomonwakhunguLink

  • FixedA Pi or OMP agent reports that it's ready once, not repeatedly. A community contribution.

    A Pi or OMP seat's runner prints its READY line once per ready transition.

    #1401 · thanks @ivanenevLink

TUI 2

  • ChangedThe TUI's Feed shows updates for a person as "No action needed" cards, most critical first. A community member's earlier work, finished here, toward a community member's report.

    The TUI's Feed shows open updates addressed to a person as "No action needed" cards, critical first, even without a Slack delivery receipt, and no longer shows one twice.

    #1054 · thanks @rudycelekli, @Aschenbath · reported by @d3fvxlLink

  • FixedOn Linux, opening an agent's terminal from the shared TUI inside Herdr now works. A community contribution.

    On Linux, opening a seat's terminal from the shared TUI viewed in a Herdr pane opens it in that Herdr instead of failing.

    #1356 · thanks @AdamWhitehurstLink

CLI & hosts 6

  • AddedReading an agent's screen now says whether the text in its input box was typed or is the harness's suggestion.

    rig capture notes on stderr whether the text in a Claude Code or Codex input box looks typed or looks like a faint harness suggestion; stdout is unchanged, and --json and the MCP tool carry an inputBox field.

    #1490Link

  • AddedEach account in provider status now says whether its sign-in looks usable.

    Each account row in rig provider status, its JSON and the TUI usage view shows a sign-in fact (usable, needs sign-in or unknown) from evidence a refresh already holds; a signed-in Claude login never reads better than unknown. A signed-out Codex login reports not_signed_in instead of rpc_error.

    #1508Link

  • ExpandedWith usage windows on, a Codex account's last reading survives a daemon restart, marked as history.

    With provider.usage_windows on, a Codex account's last reading, its reset and its last observed exhaustion survive a daemon restart and a login switch. After a restart, rig provider status shows the last reading as history ("kept from before the daemon restarted; not a current reading") with availability unknown until a fresh read; when a window's reset has passed, it shows an expectation that the window is full again, which is planning, never a reading. Rows add accountHistory, lastObservedExhausted, retained and savedProfile.

    #1535Link

  • ChangedThe capability map explains comparing token use across machines.

    The capability map explains comparing token use across machines with rig usage top.

    #1505Link

  • Fixedrig doctor's cmux warning now gives a fix that works.

    rig doctor's cmux warnings give a fix that works: set Socket Control Mode to "Automation mode" in cmux, then run rig doctor again.

    #1514Link

  • FixedProvider and compaction errors now say what went wrong and what to run, and the README says more about what OpenRig writes.

    rig provider prints the daemon's error message instead of a bare code, and rig compact's refusal for an unrecorded protected pane names rig reconcile-session <session> --no-launch. The README's "What OpenRig changes on your machine" says when Codex hook configuration is written, that your own Claude status line is kept, and which settings files are preserved.

    #1510Link

Specs & bundles 5

  • ChangedA team name with a dot is now refused before anything launches, instead of starting agents OpenRig can't reach. A community contribution.

    A rig name with a dot is refused before anything launches. tmux turns . into _ in a session name, so a seat in demo.v2 ran as …@demo_v2, where OpenRig couldn't reach it, and its tmux session was left behind. rig up, adding a member, a first-start retry, bundle install, expand and the preflight preview now refuse with a message naming the name tmux would create. An existing rig whose name has a dot gets this refusal when you add a member or retry its first start.

    #1500 · thanks @Nikhi00718Link

  • FixedThe API names the file a guidance block is really in. Reported by a community member.

    The node-detail API's targetPath names the file a guidance block is really in, and only while that file holds the block, instead of echoing the spec's declared target.

    #1523 · reported by @reisalbuquerqueLink

  • FixedThe web UI shows an aborted workflow as aborted, not completed. A community contribution.

    The web UI shows an aborted workflow as ABORTED, not COMPLETED.

    #1276 · thanks @alxledesmaLink

  • FixedA workflow that runs again no longer keeps its old finish time. A community contribution.

    A redriven workflow no longer keeps its old completion time while it runs again.

    #1517 · thanks @Vaishnavi220506Link

  • FixedThe warning for an edited generated file now suggests fixes that exist.

    The warning for an edited projected file gives remedies that exist: fold the edit into the spec, or move the file aside before the next projection. There's no --force flag.

    #1512Link

Context & skills 1

  • ChangedAgents started from the shipped specs now report their role instead of "not declared".

    The shipped agent specs mark their role file as the seat's role. After a seat's next fresh launch, rig queue whoami --json reports its role instead of not-declared, and refocus names the role file. The agent startup guide shows how to remove a leftover shared role block that a kernel installed before 0.6.5 may have left in CLAUDE.md or AGENTS.md.

    #1522Link

Setup & platform 7

  • AddedGetting started lists Rig HQ, a read-only viewer for teams. OpenRig hasn't tested it. Rig HQ is built by a community member.

    Getting started lists Rig HQ, a community-built read-only viewer for rigs; OpenRig hasn't tested it.

    #1515 · thanks @dmeloLink

  • ChangedAfter upgrading the CLI, restart the daemon so it runs the new version. One small database change runs and keeps your data.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. One database migration runs on every upgrade: 117 adds an empty, Codex-only provider_account_readings table. It fills only with provider.usage_windows on (off by default), and then keeps each resolved Codex account's usage readings across a restart. There's no migration 116. If you're coming from 0.6.11 or earlier, read 0.6.12's notes first: its twelve migrations run on the first start.

    #1535Link

  • ChangedOn Linux the daemon lists processes itself, using far less CPU at rest, in its author's measurements. A community contribution.

    Lighter on Linux: the daemon reads /proc itself, on a worker thread, instead of forking ps to list processes. The author measured CPU per listing dropping from about 69 ms to 8.4 ms, about 1.5 s of CPU a minute less at rest. macOS still uses ps.

    #1385 · thanks @SethhhhhhhLink

  • ChangedThe one-line installer now says when the CLI installed but setup isn't finished, and that running setup again is the fix.

    The one-line installer no longer calls an unfinished setup a failed install. When rig setup (step 4) doesn't finish ready, it now ends with INSTALLED, SETUP NOT COMPLETE (exit N)., the CLI's path, whether the Node.js and SQLite check passed, a pointer to setup's "Some steps need attention" list, and "run rig setup again; the CLI does not need reinstalling". Setup's exit status is kept, and steps 1 to 3 keep their FAILED [n/4] line. No dependency changes.

    #1547Link

  • ChangedThe docs now say one Claude Code or Codex account is enough, and the rigs skill lists what starting OpenRig writes.

    Getting started and the README: one working Claude Code or Codex account is enough, and the rigs skill lists what starting OpenRig writes.

    #1539Link

  • ChangedThe docs say how to install Node.js on a Mac where you aren't an administrator, and what the registry's checks decide.

    On a Mac where you aren't an administrator, or where Homebrew belongs to another account, the docs say to install Node.js with nvm in your own home. The publishing guide says what the registry's checks decide: a submission whose name is taken is still received, with a hint; a team sharing a listed team's rig.yaml name passes with a notice for the maintainer; and listing is the maintainer's decision.

    #1557Link

  • ChangedNew regression checks cover compaction and refocus, and a test no longer expires on a calendar date.

    Regression checks tie a managed /compact to its hook effect and parked work to the refocus context; a test fixture no longer expires on a calendar date; and development main carries 0.6.12's versions and release text.

    #1538, #1559, #1558Link

Known issues: 21 for this release. Read them
  • On a Mac with more than one user account, a second user's rig commands can reach the first user's OpenRig. A second user's commands can reach the first user's daemon on its default port (7433). Running each user's daemon on its own port lets both people work, but it doesn't keep them apart. This release doesn't change it.
  • After an upgrade from an older install, some managed seats can refuse rig send with "Managed pane identity unavailable or changed; no input written." Nothing is typed into the seat. Seats that 0.5.x launched recorded their tmux session but not its pane, and 0.6.x needs the pane before it sends. This was seen upgrading one install from 0.5.0 to 0.6.12; that install stays rolled back, and older installs weren't qualified for this release. Not every older seat is affected: one that was adopted or rebound since can already hold its pane. The same code is in 0.6.12, so it isn't new in this release, and this release doesn't include a repair. Don't upgrade an install whose seats a 0.5.x or older OpenRig launched without checking that they still take rig send.
  • A fresh in-place handover of a Claude seat can still report ready early in some cases: a screen without a header whose process list can't be read, a Claude process seen but not proven, or a pane or screen that can't be read. Check that the successor read its packet (#1553, #1544).
  • Managed compaction failed in two of six runs on 0.6.12 (an approval stopped the recap save; the restore map arrived after the preparation deadline), and the code involved is unchanged here. On this release's tests a manual compaction ran in order on three installs, two of them needing approvals answered during preparation; the automatic threshold wasn't run. Confirm that a compaction ran by the restore request or the drop in context. Its command budget is still 600 characters, set from one Claude Code comparison (#1483).
  • After a compaction, refocus may not show the agent's current work. On this release's tests it failed on Claude seats: for active work its trace reported a gap, and for parked work it showed a general fallback. Codex refocus wasn't run. The work packet that would carry it stays off (#1542).
  • A restore can report partially_restored: on 0.6.12 and again on this release's tests, the seats meant to be running came back (three with their original conversations here), and a deliberately stopped seat was left awaiting a decision. Launching that seat fresh works, but it starts a new conversation.
  • Two plugin hook runs for the same seat aren't serialized, and the plugin's own manifest hooks still call bare node, so a Claude session with an older PATH can still show a Stop-hook error from them (#1344, #1475, #1545).
  • Slack recovery: missed replies in older open threads aren't caught up; slack-thread-coverage.json isn't pruned yet; a default-channel backlog can drain at up to about half its earlier rate while threads also need calls; and a downgrade to an older release and back inside a rate-limit window can let other channels call Slack during that window (#1536).
  • One Slack app across machines hasn't run on two real machines. Relayed events are trusted from the calling daemon, a relay that keeps being refused is retried with no limit, rig slack verify on the hub doesn't check relayed channels, and an answer from a seat other than the one the message reached still posts at the top level (#1436).
  • rig seat set-cwd checks the new folder once: a refusal can leave the folder created, and background work, such as a Claude seat's collector files or a managed compaction's restore map, can use the saved folder before you switch. Switch promptly, and don't run rig down/rig up or a fork handover first (#1498).
  • An OMP seat releases needs-input for any failure carrying one of the seven transient statuses, including an authentication failure that carries one; untyped errors and Pi seats keep attention (#1550).
  • A send to a seat can still be refused for a quoted permission prompt that isn't really waiting, outside the Codex layout #1548 covers; and a fresh running hook still sends into Claude's MCP approval menu (#1549).
  • rig policy current and plain rig ps don't show a policy stored with rig policy apply --seat; rig seat status and pod-aware export do (#1285).
  • env: and --env values aren't secret, members added later with rig grow can't carry a member-level env:, and rig up --env is not forwarded for flat-node specs or v1 bundles (#1294).
  • The draft-aware typing guard waits for idle inside the seat's delivery lease when the input box is empty, which can delay other work for that seat, and it can't guard text a person types in the instant before OpenRig types (#1481).
  • A Claude account's availability reads unknown with usage windows on, and its sign-in fact never reads better than unknown (#1504, #1508).
  • A restore starts seats one after another, so each seat that never draws its screen adds about the readiness timeout (#1359).
  • A delivery already in transport when its watchdog stops still completes, with its records (#1325).
  • The openrig-user skill's subscription section mentions apps that don't ship; don't look for them (#1450).
  • With bundle.services_enabled on, rig up <file>.rigbundle installs into the current folder when you don't give --target (#1474).
  • Carried from earlier releases:
    • rig seat restart --keep-conversation supports Linux only.
    • The rig status API can call a running rig blocked because of one seat that isn't running (#1141).
    • A Codex seat can keep reading as at its usage limit in a constructed screen case that hasn't been seen in a real session (#1185).
    • After rig scope slice create says it couldn't verify membership, the slice was kept. Check mission.yaml before creating it again (#1007).
    • The first-install check is limited: Claude Code reached a team on a reused Mac account, not a new Mac; Codex installed but didn't reach a team after the person chose restricted settings; and a person's own registry submission wasn't run.
    • A second session in the same folder can misread a running team; the operator can point a person without a display at the shared dashboard without saying how to open it; the skill installer may not select Claude Code when it detects another agent; rig doctor checks both harnesses; rig tui --shared attaches on the default tmux server; a team's first steps can still ask for approval; a seat waiting at a permission prompt shows no product notice of its own; a launched team writes into its working folder; a resumed Claude seat can't be confirmed after /clear, an in-process /resume or a hand-started process; Codex team seats don't ask before lifecycle commands; the send gate trusts the latest recorded hook; and after a restart rig status shows Kernel: skipped.
    • A Claude Code seat whose permission request was approved automatically can still read "needs input"; the Codex case is fixed (#943, #896).
    • Slack recovery doesn't cover private channels or direct messages.
    • Older issues: the starter's Codex reviewer needs a Codex newer than 0.145; a restore can report a problem with a seat that works (#273); a claude alias defined only in a nushell rc doesn't resolve; after a reboot, start the daemon with rig daemon start and bring your rig back with rig up <name> --existing; the web UI's file preview runs scripts, so preview only files you trust; browser access isn't complete browser isolation; and Codex network inside the sandbox hasn't been checked with real logins, managed policy bundles or on Linux.
OpenRig 0.6.12MCP apps can work your team's queue, you can see what each seat costs, and commands start several times faster.24 added4 expanded46 changed50 fixed

25 contributors · Release notes

Highlights

  • AddedAn agent without a shell can now create, claim and update tasks through OpenRig's MCP tools.

    An agent with no shell can hand work to the team through rig mcp serve, which gains five queue tools (rig_queue_create, rig_queue_show, rig_queue_list, rig_queue_claim and rig_queue_update), acting as the seat named by OPENRIG_SESSION_NAME. Nothing wakes such an agent; it sees new work when it checks.

    #1441Link

  • AddedSee what each agent reports it costs beside its tokens, on the command line or in the TUI. A missing figure says so, never $0.

    rig usage cost [--seat <session>] [--json] shows what each seat's harness reports about cost beside its tokens: for Claude, the status line's own estimate for the current session (labelled an estimate, not an invoice); for Codex, tokens and a note that Codex reports no cost. A missing figure reads "not reported", never $0. It needs no setting, and the TUI's new System → Cost page shows the same lines.

    #1233, #1261Link

  • FixedClaude agents now actually run the hooks OpenRig ships for them: the activity relay, compaction save and restore, and refocus. It needs Claude Code 2.1.280 or later. A community contribution.

    Claude seats now run the hooks of the bundled openrig-core plugin, which goes from 0.1.9 to 0.1.13. A Claude seat whose plugins include openrig-core (every agent spec OpenRig ships selects it) starts with CLAUDE_CODE_PLUGIN_DIRS pointing at OpenRig's copy, so its activity relay, compaction save and restore hooks, and refocus actually run. Before, the plugin was copied to a folder Claude Code doesn't load. It needs Claude Code 2.1.280 or later; an older Claude Code ignores the setting, and OpenRig doesn't check the version. A running seat picks it up at its next launch, restore or handover. The refocus hook may now take up to 60 seconds instead of 5, so a refocus that hangs can hold up a prompt for up to a minute.

    Two plugin hook runs for the same seat aren't serialized: if a harness overlaps them, a post-compaction record can be lost or a refocus delivered twice. Overlapping runs weren't tested, and the samples that showed no prompt stall don't show that overlaps or stalls can't happen.

    #1344, #1475 · thanks @AdamWhitehurstLink

  • ChangedBringing your teams back with the last-used option now leaves down a team you stopped on purpose, and tells you how to start it. A community contribution.

    rig start --last leaves down a rig you stopped on purpose with rig down or rig seat stop, and prints how to bring it back (rig start --rigs <rig>); --json carries keptDown. --all, --rigs and the picker are unchanged. After rig down, rig ps and the TUI read the rig stopped instead of recoverable, and the printed restore command is rig up '<name>' --existing, which works even when the name matches a shipped starter.

    #1238, #1254, #1425 · thanks @adampogLink

  • AddedSet one agent's reasoning effort without editing the spec. It applies at the agent's next start, and nothing restarts.

    Set one seat's reasoning effort: rig seat set-effort <seat> --effort <level> --reason "<why>" (or --clear) saves it, and it's used at the seat's next launch, restore, handover or in-place Codex restart; nothing restarts. rig seat effort <seat> reports what was requested, what's saved, what the running process was launched with and what the session recorded.

    #1209Link

Also in this release 119

Seats & restore 13

  • AddedChange an existing agent's permission policy without editing the spec. It applies at the agent's next start. A community contribution.

    Change an existing seat's permission policy: rig policy apply <policy> --seat <seat> --reason "<why>" stores it for the seat's next restore, resume or launch. The running agent and the spec file don't change.

    rig policy current and plain rig ps don't show a policy stored with rig policy apply --seat; rig seat status and pod-aware export do.

    #1285 · thanks @danielkuykendall23-boopLink

  • ExpandedLaunch a team by its name, not only its ID, on this machine or another.

    rig launch takes a rig's name as well as its ID, locally and with --host. A name two active rigs share stops before anything is sent and lists their IDs (rig_ambiguous). Before, it took only an ID, and a name failed with not found.

    #1312Link

  • ChangedAn ordinary terminal agent now starts fresh on every restore instead of stopping to ask each time. A community contribution.

    An ordinary terminal seat relaunches fresh on restore and re-runs its startup actions, instead of stopping at awaiting-decision on every restore after its first. A required startup file missing for such a seat now blocks the whole restore before anything launches (required_startup_file_missing).

    #1328 · thanks @AdamWhitehurstLink

  • ChangedA restore now stops an agent whose harness changed since its snapshot, before opening its terminal. A community contribution.

    Restore stops a seat whose current runtime differs from the one its snapshot started with, before creating its terminal session, and --fresh doesn't bypass it.

    #1190 · thanks @haralezLink

  • ChangedA Claude agent that's slow to start now ends as needing attention, not failed, with its pane kept so you can look. A community contribution.

    A slow start ends as needing attention, not failed. A restored Claude seat that hasn't drawn its screen is watched for up to runtime.readiness_timeout_seconds (30 s by default) and then ends attention_required with its pane and attempted resume token kept, so a restore can take longer: up to about 27 seconds more for each seat that never starts, one after another. A seat is described as "returned to a shell" only when the process tree shows an idle shell, and the older restore path for rigs without pods keeps such a seat for attention instead of rolling it back.

    A restore starts seats one after another, so each seat that never draws its screen adds about the readiness timeout.

    #1359, #1357, #1395, #1373, #1364 · thanks @AdamWhitehurst, @shravansumanthananLink

  • ChangedAdding or launching agents now waits up to two minutes for a busy daemon instead of five seconds. A community contribution.

    rig add, single-seat rig launch (including --retry-startup-from) and rig launch --seats wait up to 120 seconds for the daemon instead of 5. A timeout there still isn't a rollback, so check rig ps before running it again.

    #1287, #1271 · thanks @AdamWhitehurst, @haralezLink

  • ChangedRemoving or shrinking a team no longer loses work that arrives while an agent is stopping. A community contribution.

    rig remove and rig shrink keep a seat that receives work while it's being stopped: the late work goes to your --fallback, or the stopped seat is kept and the command answers 409 with the work listed. A stale rig unclaim that would detach the seat's newer occupant is refused with 409 session_not_current.

    #1459, #1379 · thanks @Nikhi00718Link

  • FixedAn agent whose startup stalled now recovers on its own once a message or capture gets through. A community contribution.

    A seat whose startup failed for a recoverable readiness reason becomes ready after a successful send or capture.

    #1236 · thanks @shravansumanthananLink

  • FixedTaking a team down no longer lets a mid-shutdown snapshot replace the full one taken before it. A community contribution.

    A periodic snapshot taken while rig down was stopping a rig no longer replaces the complete pre-down snapshot.

    #1147 · thanks @Vaishnavi220506Link

  • FixedWhen OpenRig can't confirm which process is an agent, it now says what it found. A community contribution.

    A failed process-lineage check says what it found (for example, that the running Codex was launched with a different conversation than the seat records), instead of blaming the pane's foreground label.

    #1398 · thanks @AdamWhitehurstLink

  • FixedSession checks no longer report drift for a Claude or Codex agent whose terminal reads sh. A community contribution, fixing a community member's report.

    rig reconcile-session no longer reports a runtime drift for a pane reading sh when Claude or Codex is running in it.

    #1395 · thanks @AdamWhitehurst · reported by @davey64Link

  • FixedSetting an agent's resume token works even after the system clock moved backwards. A community contribution.

    rig seat set-resume-token writes to the seat's latest session even after the system clock moved backwards.

    #1204 · thanks @XTLineLink

  • FixedWhen cleaning up an agent is refused, the advice now names the right session. A community contribution.

    When rig seat clean refuses because an older session is still alive, its advice names that session instead of suggesting rig seat stop, which would act on the current occupant.

    #1206 · thanks @XTLineLink

Queue & messaging 20

  • AddedCorrect a task's subject at any time with one command. A community contribution, fixing a community member's report.

    rig queue update <id> --summary "<text>" on its own corrects a row's subject in any state.

    #1270 · thanks @Totopo27 · reported by @psbankaLink

  • AddedRecord how a task turned out when you close it, and read it back later. A community contribution.

    rig queue update <id> --state <closing state> --resolution "<outcome>" stores the outcome on the row, rig queue show returns it, and a later fallback adds its line instead of erasing it.

    #1292 · thanks @AdamWhitehurstLink

  • AddedA closed task now shows who closed it, when, why and with what note. A community contribution.

    rig queue show <id> --full on a closed row adds closingTransition: its state, reason, target, who closed it, when, and the closing note.

    #1290 · thanks @AdamWhitehurstLink

  • AddedA new setting, off by default, makes a verified send to Claude Code or Codex check the input box before it says verified. A community contribution.

    Off by default: transport.verify_input_box (OPENRIG_TRANSPORT_VERIFY_INPUT_BOX). A --verify send to Claude Code or Codex reads verified only when the text was seen in the input box and the box was empty after Enter. It only reports; nothing is retried. Multi-line sends and wakes to Claude Code stay unconfirmed.

    #1267 · thanks @alxledesmaLink

  • AddedA new per-agent typing guard, off by default, holds a message instead of typing over someone's unsent text.

    Per seat, off by default: rig seat set-typing-guard <seat> --mode draft-aware --reason "<why>" checks the input box before typing and before Enter, and holds or refuses a message instead of typing over someone's unsent text; nothing retries it. --mode hold is the existing on, and --mode off the default. The draft-aware guard's shared send and startup code runs for every seat.

    The draft-aware typing guard waits for idle inside the seat's delivery lease when the input box is empty, which can delay other work for that seat (not measured), and it can't guard text a person types in the instant before OpenRig types.

    #1481 · thanks @Aschenbath, @Mr-Neutr0nLink

  • ExpandedThe compact output setting, still off by default, now also shortens task and history views and limits the peers whoami lists.

    output.compact (OPENRIG_OUTPUT_COMPACT, off by default, from 0.6.11) now also shortens rig queue show and rig queue transitions (--full prints everything; rig queue transitions --full is new), and bounds rig whoami --json peers to output.whoami_peers (new, default 8), connected peers first; --all-peers lists everyone. Over SSH --host, the note's full-list command now names the host.

    #1224, #1225, #1248Link

  • ChangedAnswering an agent's menu now types exactly the keys you send, and adds Enter only when a complete answer is visibly staged.

    rig send --dangerously-interact types exactly the bytes and keys you give it, in any state and over every transport: a lone CR, Tab, Space or Esc acts as that key. Enter is added only when a complete answer is visibly staged in a recognised Claude Code or Codex input box; anywhere else, put CR in the payload yourself.

    #1366Link

  • ChangedTask updates you can fix now come back as plain errors instead of server failures. A community contribution.

    rig queue update refusals you can fix answer HTTP 400 and exit 1, not 500 and exit 2: eleven error codes for closure fields, blocked_on or wake options where they can't be stored, and a watchdog that isn't live or targets someone else. blocker_not_found, blocker_not_live and blocker_malformed still exit 2.

    #1319 · thanks @rudycelekliLink

  • ChangedAn agent's status now names the typing guard's mode plainly.

    rig seat status reads Typing guard: on (hold) for hold, and its JSON's desired and effective booleans now mean hold only.

    #1481 · thanks @Aschenbath, @Mr-Neutr0nLink

  • ChangedClosing a task as handed off without a clear successor now points to the handoff command, and a task closed onto itself is flagged. A community contribution, toward a community member's report.

    Closing a row as handed off without a verifiable successor now points to rig queue handoff, and the stuck sweep flags a row closed onto itself.

    #1358 · thanks @shravansumanthanan · reported by @m3ac-AllbrittenJLink

  • ChangedHelp, warnings and skills now say the summary is a task's subject, and the TUI shows a body's first line when there's no summary. A community contribution.

    Help, warnings and the shipped skills say --summary is a row's subject everywhere it's listed, and carry the project:, mission: and slice: tags; the reply hint for messages from a person includes --summary. The TUI's RECENT list shows the first line of a row's body when it has no summary.

    #1354, #1355, #1393 · thanks @AdamWhitehurstLink

  • ChangedMessaging a person when nobody is registered now tells you how to register one.

    With nobody registered, a send to a person says to register one with rig gateway human add instead of reporting a missing registry projection.

    #1219Link

  • ChangedThe coordination notes say which task fields report delivery to a terminal. A community contribution, fixing a community member's report.

    The coordination notes say which queue fields answer pane delivery.

    #1277 · thanks @alxledesma · reported by @roALAB1Link

  • FixedA message to a terminal you've scrolled back in now gets delivered, and returns that terminal to the bottom. A community contribution, fixing a community member's report.

    A send to a pane in tmux copy or view mode leaves the mode once and delivers. A pane that can't leave its mode gets no text, and the send is refused with pane_in_mode (HTTP 409). A person scrolled back in that pane is returned to the bottom.

    #912 · thanks @Coder8124 · reported by @m3ac-AllbrittenJLink

  • FixedA wake the typing guard holds back no longer uses up a one-time timer, fixing a known issue from 0.6.11.

    A held-back wake no longer uses up a one-shot park timer (0.6.11's known issue): a wake the typing guard holds back is tried again at the timer's interval, and a shared one-shot timer retires when its last attachment is consumed.

    #1222Link

  • FixedStopping a watchdog mid-check now stops it, with no late wake. A community contribution.

    Stopping or retiring a watchdog while a check is running stops it: no late wake and no late record; its last attempt's time is still recorded.

    A delivery already in transport when its watchdog stops still completes, with its records.

    #1325, #1439 · thanks @Nikhi00718Link

  • FixedA waiting task still gets its next wake when its blocker changes during a send. A community contribution.

    A waiting row whose blocker changes while an earlier wake is being sent still gets its next wake.

    #1435 · thanks @Nikhi00718Link

  • FixedA task held until its agent's own reminder is no longer flagged as stranded.

    A row parked on its owner's own repeating reminder isn't counted as stranded once the reminder has delivered, and rig parked marks it servedByOwnReminder.

    #1424Link

  • FixedA handoff between machines now records who sent it.

    A cross-host handoff's closing record carries the sender's identity, as a local one does.

    #1333Link

  • FixedOverlapping inbox absorbs make one task, not two. A community contribution.

    Absorbing an inbox entry into queue work is one transaction, so overlapping absorbs make one row.

    #1451 · thanks @Nikhi00718Link

Claude 12

  • AddedAn agent can give a slow refocus more time.

    A seat can give a slow refocus more time with OPENRIG_REFOCUS_BUDGET_MS, from 4500 (the default) to 52000 ms.

    #1475Link

  • AddedA new guide shows how to keep your own Claude status line alongside OpenRig. A community contribution, fixing a community member's report.

    A new page explains how to keep your own Claude status line with OpenRig's context collection.

    #1308 · thanks @dajiaohuang · reported by @natefaerberLink

  • ChangedThe fable alias now means Claude Fable 5.1, and a 1M-context pin no longer reads as a mismatch. Pinned Pi agents are checked too. A community contribution.

    The fable model alias now names claude-fable-5-1, so a fable pin on a seat running claude-fable-5 raises a divergence notice. A Claude pin ending [1m] no longer does when the seat runs that model. Pinned Pi seats are now checked, and a Pi thinking-level suffix such as :high doesn't count as a divergence.

    #1482, #1349, #1403 · thanks @smotaLink

  • ChangedWith managed compaction on, Claude Code no longer compacts OpenRig's sessions on its own while they're idle.

    With managed compaction on, Claude sessions OpenRig launches carry idleCompaction: false, so Claude Code 2.1.290 or later doesn't compact them on its own while idle.

    #1282Link

  • ChangedWith usage windows on, a Claude account's availability reads unknown, because a reading can't yet be tied to its login.

    With usage windows on, a Claude account's current availability always reads unknown, because nothing links a seat's reading to the login it used; each window still shows as that seat's reading.

    #1504Link

  • FixedOpenRig's managed compaction command is short again, so Claude Code takes it as a command instead of pasted text. Toward a community member's report.

    Managed /compact is kept to 600 characters, sent only to an idle seat, and reported separately. Since 0.6.10 the managed command had grown long enough that Claude Code took it as pasted text, so it didn't run while the attempt read as delivered. The rest of the instructions move into the restore map and the restore request. rig compact and rig compact --state show a separate compact result: submitted, unconfirmed (it reached the seat; that isn't proof compaction ran), uncertain (not replayed) or not sent. A running draft-aware seat with no recorded pane is refused with pane_unknown_protected: rig compact exits 1 (was 2) and the route answers 409 (was 502). Over the shared transport, a write that throws without a code makes rig send exit 1 with HTTP 409 instead of 2 with 500.

    The command budget is 600 characters, set from one comparison on Claude Code 2.1.282 (792 characters ran as a command, 850 didn't), and a later Claude Code could move that line. Nothing confirms compaction ran; read submitted, unconfirmed as reached, and confirm by the restore request or the drop in context.

    #1483 · reported by @shintaiiLink

  • FixedClaude agents signed in through a gateway now start and restore normally; only a real login refusal counts as signed out. Reported by a community member.

    Claude login detection is narrower. Only a current refusal (Not logged in · Please run /login, Login expired · Please run /login or OAuth token revoked · Please run /login) reads login_required. The "Not logged in" footer alone no longer does, so a seat signed in through a gateway starts, resumes and restores normally.

    #1417 · reported by @archuityLink

  • FixedAutomatic compaction no longer acts on a context reading from before an agent was stopped or replaced. A community contribution.

    Automatic compaction ignores a context reading taken before a seat was stopped, replaced, handed over or restarted.

    #1365 · thanks @Nikhi00718Link

  • FixedFewer healthy Claude launches warn that their startup message wasn't confirmed. A community contribution.

    When a Claude seat's startup prompt is still unsent, the launch presses Enter up to twice, each time only while the box holds exactly that prompt, and more Claude footers are recognised, so fewer healthy launches warn "Startup submission unverified".

    #1295 · thanks @AdamWhitehurstLink

  • FixedShift+Enter adds a newline in Claude agents started with a permission mode, when tmux supports it. A community contribution.

    In a Claude seat started with a permission mode, Shift+Enter inserts a newline when tmux's extended-keys is on: the launch passes the pane's TERM_PROGRAM and TERM_PROGRAM_VERSION to Claude. The getting-started guide says how to add a newline when Shift+Enter submits.

    #1399, #1404 · thanks @AdamWhitehurstLink

  • FixedA launch no longer overwrites a project's Claude settings or MCP file that isn't valid JSON; it warns instead.

    A launch leaves a project's .claude/settings.local.json or .mcp.json untouched, with a warning, when it isn't a JSON object, instead of overwriting it.

    #1311Link

  • FixedOpenRig stops rewriting a Claude agent's settings file every 30 seconds. A community contribution.

    OpenRig no longer rewrites a Claude seat's settings file every 30 seconds when its status line is already in place, and replaces a read-only copy of its context collector instead of failing.

    #1286, #1251 · thanks @haralezLink

Codex 9

  • AddedA new setting, off by default, keeps a record of moving Codex agents between subscriptions.

    Off by default: provider.subscription_moves (OPENRIG_PROVIDER_SUBSCRIPTION_MOVES). A record of moves of a Codex home's seats between subscriptions, rig provider moves [--home|--seat|--limit], rig provider moves show <id> and rig provider moves record --file <json|->, plus a section of the openrig-user skill for an agent a person asks to manage subscriptions. While it's off, the commands exit 1 and the routes answer 409.

    The openrig-user skill's subscription section mentions apps that don't ship in this release; don't look for them.

    #1450Link

  • AddedThe agent startup guide explains how a Codex agent compacts. A community contribution.

    The agent startup guide explains how a Codex seat compacts and how to size it.

    #1340 · thanks @AdamWhitehurstLink

  • ChangedA daemon that never runs Codex no longer writes to your Codex config. A community contribution.

    The daemon writes Codex's config.toml only when a Codex seat exists or launches, so a daemon that never runs Codex leaves ~/.codex/config.toml alone.

    #1297 · thanks @AdamWhitehurstLink

  • ChangedThe daemon logs why it couldn't capture a Codex agent's resume token. A community contribution.

    The daemon logs why it couldn't capture a Codex seat's resume token, once per reason, and stops those captures when it shuts down.

    #1284 · thanks @adampogLink

  • FixedA Codex agent that forks a conversation keeps its startup context even when the new conversation is slow to report in. Reported by a community member.

    A Codex seat that forks a conversation keeps its startup context when the new conversation's ID arrives late. The launch waits up to the readiness timeout for a verified child; if none arrives, the seat stops at attention_required, and rig seat continue <seat> delivers its role once. A handover to a forked Codex conversation completes with the ID marked pending instead of failing.

    #1438, #1216 · thanks @Aschenbath · reported by @m3ac-AllbrittenJLink

  • FixedA Codex agent started through a wrapper script is no longer reported as dropped to a shell while it starts. A community contribution, fixing a community member's report.

    A Codex seat started through a shell wrapper isn't reported as returned to a shell while it starts.

    #1373 · thanks @shravansumanthanan · reported by @celaya-solutionsLink

  • FixedThe Codex resume command OpenRig prints keeps the no-daemon option when the agent used it. Reported by a community member.

    The Codex resume command OpenRig prints keeps --no-daemon when the seat's last managed launch used it; for seats launched before this, the guidance says the choice wasn't recorded.

    #1371 · reported by @reisalbuquerqueLink

  • FixedOpenRig now reads Codex's input prompt, so it can tell a staged message from a delivered one. A community contribution.

    Codex's » prompt is recognised when reading an input box, so a staged message on a Codex seat can get its one guarded Enter, and rig send --verify tells a message still in a Codex input box from one that was delivered.

    #635, #1220 · thanks @Mr-Neutr0nLink

  • FixedA Codex agent shows as needing you only when its screen shows a real approval or choice. A community contribution, toward a community member's report.

    A Codex seat reads as needing a person only when its pane shows a real approval or selection prompt; an unreadable pane still gets there after a short grace, as permission_request_unverified.

    #943 · thanks @zichen0116 · reported by @floynk-agentLink

Pi 5

  • AddedTwo new settings, off by default, show Pi's own cost estimate and OpenRouter's actual charge.

    Off by default: usage.pi_cost_facts and usage.pi_openrouter_charge (OPENRIG_USAGE_PI_COST_FACTS, OPENRIG_USAGE_PI_OPENROUTER_CHARGE). Pi's own cost estimate in rig usage cost, counted once with a fork's inherited entries kept apart, and OpenRouter's actual charge beside it, never added to it. With both on, the Pi runner asks OpenRouter for each request's charge with the key OpenRig already gives the seat. A Pi seat reads both switches when it launches or resumes, so a change takes effect then; what was recorded stays visible. With every setting off, a Pi models.json notice can report a provider key's presence instead of unknown, because models.json is now read the way Pi reads it.

    #1237, #1244Link

  • ChangedA Pi or OMP agent that has dropped to a bare shell now shows as needing attention, so its team is offered for restore.

    A Pi or OMP seat whose agent has exited to a bare shell reads attention_required (process_identity_mismatch) instead of running, so rig start offers its rig as a restore candidate.

    #1391Link

  • ChangedThe spec reference notes that a HOME value reaches Pi.

    The rig spec reference says a HOME value reaches Pi's agent.

    #1335Link

  • FixedOMP agents with long histories restore and refresh correctly. Reported by a community member.

    An OMP seat's restore catch-up and history refresh work past 1 MiB of history when OMP offers its RPC protocol v2, up to 64 MiB.

    #1279 · reported by @AlexGhanemLink

  • FixedA failed Pi or OMP turn shows a usable error. A community contribution.

    A failed Pi or OMP turn shows the first usable error field.

    #1208 · thanks @XTLineLink

Slack 6

  • AddedOne Slack app can now serve several machines, and a person's message in a team's own channel goes to that team. Reported by a community member.

    One Slack app can serve several machines: the machine holding the app-level token relays the channels listed in forwardChannels to the machines that own them, and a person's answer posts in their own thread. A person's new message in a rig's own mapped channel now goes to that rig's representative (or a seat named with --inbound), and every seat post's sender line names the machine (from <seat> on <host id>), on one machine too.

    One Slack app across machines was simulated in one process, never run on two real machines. Relayed events are trusted from the calling daemon, a relay that keeps being refused is retried with no limit, rig slack verify on the hub doesn't check relayed channels, and an answer from a seat other than the one the message reached still posts at the top level.

    #1436 · reported by @mlc-factory-botLink

  • AddedNamed bots' posts in one Slack channel can go to one agent, marked as coming from a program.

    A botInbox block delivers named bots' posts in one Slack channel to one seat, as rows marked as data from a program. The app manifest asks for one more scope, users:read.

    #1433Link

  • ChangedSlack setup now says what to do when the manifest shows up empty. A community contribution, fixing a community member's report.

    rig slack manifest --help and the setup guide say how to paste the manifest when Slack shows it empty.

    #1207 · thanks @Totopo27 · reported by @a4w-h4yLink

  • FixedA workflow step waiting on a person shows them the question, not the agent's instructions. A community contribution, fixing a community member's report.

    A workflow gate waiting on a person shows that person the question, not the agent packet, and still posts when its tags are very long.

    #1143, #1240 · thanks @akushonkamen · reported by @tianqizhao0704Link

  • FixedAn agent's follow-up to a Slack button or reaction goes to the right thread. A community contribution.

    A seat's follow-up to a Slack button answer, or to a reaction on a resolved ask, lands in that ask's thread.

    #1228 · thanks @rudycelekliLink

  • FixedNotifications keep em dashes, emoji and other text as written. A community contribution.

    An ntfy notification title with an em dash, an emoji or other non-ASCII text is delivered as written, and shortened notification bodies, slice stories and rig ask excerpts keep emoji whole.

    #1317, #1472 · thanks @rudycelekliLink

TUI 3

  • ChangedThe TUI's slice header says what its proof count counts. A community contribution.

    The TUI's slice header says what its proof count counts: accepted with a judgment policy, paired without.

    #1288 · thanks @AdamWhitehurstLink

  • FixedThe TUI keeps working after the folder you started it in is deleted. Reported by a community member.

    TUI helpers keep working after the folder you started it in is deleted.

    #1485 · reported by @davey64Link

  • FixedSeveral TUI fixes: wide terminals open the default view, and trackpad swipes, emoji and the Help list behave. A community contribution.

    In the TUI, Open terminals sends the window's width, so a wide terminal opens the default view; the file reader finds headings with combining marks; the Help list stops at its last command; a sideways trackpad swipe no longer scrolls up or down; and rows cut to width keep emoji whole.

    #1205, #1471, #1469, #1458, #1453 · thanks @XTLine, @rudycelekliLink

CLI & hosts 13

  • AddedThe event stream can replay a chosen number of past events. A community contribution.

    GET /api/events takes ?replay=0|<n>|all and streams its replay 500 events at a time; the default is unchanged.

    #1387 · thanks @SethhhhhhhLink

  • ExpandedThe usage windows setting, still off by default, now also shows Claude's 5-hour and weekly windows, each agent's account and every machine's windows.

    provider.usage_windows (OPENRIG_PROVIDER_USAGE_WINDOWS, daemon, off by default, from 0.6.11) now also shows Claude's 5-hour and weekly windows from the seats' status lines in rig provider status, with --provider codex|claude to limit a refresh; each seat's configured account; and, with --all-hosts or --hosts <ids>, every registered machine's windows, listed once per allowance and never added up. The TUI's System → Usage and Usage · all hosts pages are always listed and, with the setting off, say how to turn it on.

    #1197, #1235, #1246, #1243, #1259Link

  • ChangedAsking about a team that doesn't exist, or a name two teams share, now exits as an error instead of a success. A community contribution.

    rig ask exits 1 for an unknown or ambiguous rig instead of 0.

    #1202 · thanks @Coder8124Link

  • ChangedThe rig command starts several times faster, in its author's measurements. A community contribution.

    The CLI starts faster: it loads only the command being run and turns on Node's compile cache, so rig queue list and rig ps start several times faster in the author's measurements.

    #1380 · thanks @SethhhhhhhLink

  • ChangedA failed create now says why in its JSON.

    rig create --json says why a create failed, in detail.

    #1378Link

  • ChangedStatus as JSON now comes back as one object, and an unconfirmed daemon isn't reported as down. A community contribution.

    rig status --json prints the daemon, kernel, workspace root, rigs and cmux state as one object; daemon.reachable: null means unconfirmed, not down.

    #1291 · thanks @AdamWhitehurstLink

  • ChangedReads that cut lines or skip a filter now say so. A community contribution.

    rig capture --lines N that cut lines says activity is unknown, on stderr and as activity: "unknown" in --json. rig ps with a context-usage filter but no --nodes says on stderr that the filter wasn't applied.

    #1226, #1437 · thanks @Vaishnavi220506Link

  • ChangedSaved modes and work postures can sit side by side, and mode output marks fields nothing acts on yet.

    rig mode keeps a saved mode and a work posture side by side at one target, and rig mode unset --category mode|posture removes one; the rig mode set preview reads an unusable answer as unknown; and rig mode's human output marks the eight saved fields nothing in OpenRig acts on yet.

    #1274, #1283, #1307Link

  • FixedUsage rankings no longer count a new conversation or a reset window as burn, so the numbers follow real use. A community contribution, fixing a community member's report.

    rig usage top no longer counts a new conversation, or a reset window, as burn. Tokens and rates are measured within one history and one window, so figures can drop and rankings change, and it no longer shows a negative rate after a window resets.

    #1348, #1473 · thanks @Nikhi00718, @rudycelekli · reported by @d3fvxlLink

  • FixedA stopped agent's transcript stops capturing and stays readable at any age. A community contribution.

    A stopped or removed seat's transcript capture stops, and its saved transcript stays readable at any age. A quiet seat's transcript health can read live with reason capture_unchanged while its last capture is more than 10 seconds old. rig transcript --tail N no longer cuts off the first requested line.

    #1281, #1262, #1227 · thanks @Sethhhhhhh, @Quentin-M, @oodadoudouLink

  • FixedMachines on IPv6 read as reachable, and the web UI keeps emoji whole. A community contribution.

    GET /api/hosts reads an IPv6 HTTP host as reachable when it is. The web UI's Log page keeps emoji whole in shortened previews.

    #1457, #1454 · thanks @rudycelekliLink

  • FixedUsage and bundle history say when a date bound isn't a date. A community contribution.

    rig usage series --since/--until and rig bundle history --since say when a bound isn't a date or time.

    #1305, #1306 · thanks @Coder8124Link

  • FixedThe daemon answers a handful of bad requests with clear errors instead of failures. A community contribution.

    Requests the daemon now answers cleanly: a route given a JSON body of null answers 400 invalid_json instead of 500; a limit of 2^63 or more on queue overdue and usage series answers 400; chat search behind rig ask matches _ and % literally; rig restore's not-found hint gives the working rig snapshot list <rig>; rig watchdog register warns when a cadence such as 5m will be read as 5 seconds; and rig whoami --host <id> --full forwards --full, which a remote older than v0.4.0 refuses.

    #1342, #1456, #1455, #1466, #1463, #1231 · thanks @rudycelekliLink

Specs & bundles 15

  • AddedGive a team environment variables in its spec; they reach every agent and survive restores. The values aren't secret. A community contribution.

    Give a team environment variables in its spec: an env: block on the rig and on any member in rig.yaml reaches every seat, including Claude Code's cleared environment, carries into restores and handovers, and rig export writes it back. rig up <spec> --env KEY=VALUE adds a value for one launch. Names match ^[A-Z_][A-Z0-9_]*$, and OPENRIG_* is reserved. The values aren't secret: they're stored in OpenRig's database and snapshots and copied by export and bundles.

    Members added later with rig grow can't carry a member-level env:. rig up --env is not forwarded for flat-node specs or v1 bundles, although the launch may succeed. Do not rely on the flag for those formats in this release.

    #1294 · thanks @AdamWhitehurstLink

  • AddedA new setting, off by default, lets a bundle carry services and shows them before anything runs.

    Off by default: bundle.services_enabled (OPENRIG_BUNDLE_SERVICES_ENABLED). A bundle carries its declared Compose file, rig bundle inspect shows each service before anything runs, and rig up and rig bootstrap install it into a lasting target folder.

    With bundle.services_enabled on, rig up <file>.rigbundle installs into the current folder when you don't give --target.

    #1474Link

  • AddedWorkflows can carry a project, mission and slice, so their work shows on the slice's Queue tab. A community contribution.

    rig workflow instantiate and rig workflow run take --project, --mission, --slice and --tags, stamped on every packet so the work shows on the slice's Queue tab; instantiate-lifecycle takes them from the lifecycle. An unknown project creates the instance unscoped with a warning.

    #1273 · thanks @AdamWhitehurstLink

  • ExpandedA workflow can address whichever team it's bound to, and an edited workflow spec is picked up after a restore. A community contribution.

    A workflow's preferred_targets entry can be written member@{rig} to address whichever rig the instance is bound to. An edited workflow spec restored with an older modification time is picked up.

    #1293, #1363 · thanks @AdamWhitehurst, @Vaishnavi220506Link

  • ChangedBundles now refuse harness login files, so a shared team doesn't carry your sign-ins by accident.

    rig bundle create refuses harness login files (.claude/.credentials.json, .codex/auth.json, .pi/agent/auth.json) anywhere in an agent folder or carried project. An existing archive holding one without a record now fails verify, unpack and install; install answers 400 even with --force. rig bundle create --include-login-files includes those files only when recipients should have them and the login's owner agrees, and records their paths as included_login_files.

    #1488Link

  • ChangedA new mission starts as planned, so it stays out of the project's progress until you make it active. A community contribution, fixing a community member's report.

    rig scope mission create writes status: planned, which keeps a new mission out of the project's proof rollup until you set it active. With --workspace <project> it creates the mission inside that project, under its declared missions.root, which now wins over a missions/ folder for every command that reads missions.

    #1289, #1430 · thanks @AdamWhitehurst, @dajiaohuang · reported by @kainne44Link

  • ChangedThe execution view matches tasks to missions and slices by their exact tags and ids. A community contribution.

    The execution view binds a queue row to a mission by its exact mission: tag first, and a slice: tag can name a slice by its SPEC id: as well as its folder.

    #1304, #1331 · thanks @AdamWhitehurstLink

  • ChangedThe execution view shows waiting slices and merged work more accurately. A community contribution.

    The execution view shows a slice parked on an external: gate as a waiting lane, and shows a merged:<pr> report on the merged rung, counting it as merged only with a candidate:<sha> that matches the slice's built commit. A slice dependency can name a sibling by its SPEC id:.

    #1303, #1302, #1372 · thanks @AdamWhitehurstLink

  • FixedBootstrap and requirements find a relative spec path from your own folder. A community contribution.

    rig bootstrap and rig requirements resolve a relative spec path from your own folder when the target is this install's local daemon.

    #1213 · thanks @XTLineLink

  • FixedFiles saved with Windows line endings read the same as Unix ones across project files. A community contribution.

    Files saved with Windows (CRLF) line endings read the same as Unix ones in SPEC.md intents, checkbox blocks, PROGRESS.md, proof and review headers and artifact-pool watchdog reads.

    #1316, #1315, #1314, #1402, #1322 · thanks @rudycelekli, @Jacob-9909Link

  • FixedThe Scopes view reads more proof and requirement formats. A community contribution.

    The Scopes view reads a proof drop's folded evidence references and mini-requirements numbered 1). The daemon's scope audit answers "mission not found" for a mission name that leads outside the slices root.

    #1461, #1460, #1221 · thanks @rudycelekli, @DeryFerdLink

  • FixedAn agent's own mechanic setting survives bundling. A community contribution.

    A member's own mechanic survives bundling and other spec rewrites.

    #1464 · thanks @rudycelekliLink

  • FixedA blank list item in a spec gets a clear error instead of a crash. A community contribution.

    A blank list item in a rig spec, agent spec or startup files: list gets a validation error at its path instead of a crash, and an agent spec profile written as a bare key reads as an empty profile.

    #1318, #1320 · thanks @rudycelekliLink

  • FixedContext packs and agent images accept file names with two dots. A community contribution.

    Context packs and agent images accept file names with two dots inside a name, such as notes..md; a real .. segment is still refused.

    #1234, #1465 · thanks @rudycelekliLink

  • FixedEmpty Docker Compose results and macOS file copies report correctly. A community contribution.

    An empty Docker Compose ps result reads as no services instead of unparseable output. On macOS, rig file copy reports how many bytes it copied.

    #1452, #1232 · thanks @rudycelekliLink

Context & skills 7

  • AddedFor Codex users, the rigs skill offers an optional, removable rules file so common rig commands don't ask for approval.

    For a Codex user, the rigs skill makes one optional offer of a removable rules file so six rig commands run without approval prompts.

    #1467Link

  • AddedAsk the operator to watch something or remind you, including a warning when your allowance runs low.

    The operator reads the keeping-a-watch page when a person asks it to watch something or remind them, and the page teaches a "warn me when my allowance runs low" watch.

    #1217, #1266, #1268Link

  • ChangedSetting up through the rigs skill now offers to join your own Claude Code or Codex to the team, so the operator knows who it's talking to.

    The rigs skill has a person's own Claude Code or Codex offer to join the team before its first message to the operator, so the operator sees a named teammate; inside tmux it says the effects first and the person chooses.

    #1492, #1496Link

  • ChangedSetup rechecks a failed network check before asking you to sign in again, and the operator offers the Workshop configuration that fits your harnesses.

    Setup re-checks a failed network check with network access before asking anyone to sign in again, installs through rig setup, and the operator offers the Workshop configuration that fits the person's providers.

    #1434Link

  • ChangedSkills now say to brief a peer for the model it runs, and can wake an attached app's agent when work arrives.

    delegating-work says to brief a peer according to the model it runs, which rig ps --nodes --json shows as model. The openrig-user skill adds an opt-in loop that wakes an attached app's agent when work arrives. rig ask --wake help and two skills explain the target forms.

    #1486, #1444, #1426Link

  • ChangedOpenRig now says "harness" for the agent software around a model, and defines the term.

    User-visible text says "harness" for the agent software around a model, and "community harness" for one an outside contributor maintains; docs/reference/topology-naming.md defines the terms.

    #1506Link

  • ChangedContributor docs point agents to the developing-openrig skill and link the public roadmap.

    The README points contributors' agents to the developing-openrig skill, the roadmap links the public board, and the contributor guides describe the one-home skill workflow.

    #1370, #1423, #1432Link

Setup & platform 16

  • AddedA new daemon option, off by default, sends routine tmux commands through one long-lived connection. A community contribution.

    Daemon environment, off by default: OPENRIG_TMUX_CONTROL=1 sends the daemon's routine tmux commands through one long-lived control client.

    #1383 · thanks @SethhhhhhhLink

  • AddedList installed community harnesses, with their maintainers and limits. OpenRig doesn't test them, and support is launch-only.

    OpenRig 0.6.12 adds rig community-harness list for installed community-harness presets, showing their maintainer and declared limits. These harnesses are not tested by OpenRig. Support is launch-only: no resume or fork, no resource projection or startup-file delivery, and identity remains unconfirmed. A quiet screen is not proof that the seat is idle.

    #1392, #1518Link

  • ChangedAfter upgrading the CLI, restart the daemon so it runs the new version. Twelve small database changes run on the first start and keep your data.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. Twelve database migrations run on the first start, whatever you use: 100 (the typing guard's mode columns), 104 (nodes.effort_choice), 105 (two usage_samples columns for Claude's cost estimate), 107 and 108 (Pi usage entries and charges), 109 (the mode store's unique index per category, keeping every row), 110 (workflow_instances.scope_json), 111 (rigs.env_json and nodes.env_json), 112 (two indexes for recent queue activity, about 10 to 12 MB on a long-running install), 113 (applied_launch_observations.daemon_opt_out), 114 (sessions.agent_app) and 115 (the Slack thread map rebuilt by channel and thread timestamp, keeping existing rows). There are no migrations 102 or 106, and no earlier migration was changed.

    #1481, #1209, #1233, #1237, #1244, #1274, #1273, #1294, #1326, #1371, #1392, #1436 · thanks @AdamWhitehurstLink

  • ChangedA harness that hangs on its version check no longer keeps the daemon from starting; the check gives up after 30 seconds. A community contribution.

    A runtime's --version check gives up after 30 seconds. At daemon start a hung probe no longer keeps the daemon from listening, and rig bootstrap now blocks on a runtime that is installed but fails or times out its check, which it reports apart from one that's missing. rig up's preflight fails a Claude, Codex or OMP check that doesn't answer within 30 seconds (a warning for Pi), and stopping the daemon ends the probes it started.

    #1211, #1301 · thanks @AdamWhitehurstLink

  • ChangedThe daemon now runs tmux directly instead of through a shell, one reason it does less work. A community contribution.

    On Linux and macOS, the daemon runs tmux directly instead of through /bin/sh. Set OPENRIG_TMUX_SHELL=1 when starting the daemon to keep the old path.

    #1241 · thanks @Quentin-MLink

  • ChangedThe daemon does much less work on a busy machine. A community contribution, fixing a community member's report.

    The daemon does much less work on a busy machine: it runs tmux without a shell, captures up to 24 transcripts in one tmux call, skips reading terminals that haven't changed, and reads queue activity and obligations with far fewer queries. The timings are the authors' own.

    #1241, #1242, #1262, #1263, #1326, #1369, #1384, #1389 · thanks @Quentin-M, @Sethhhhhhh · reported by @korallisLink

  • ChangedDependency changes are small: no new package to install, and the Node requirement is unchanged. A community contribution.

    The daemon now declares string-width (^8.3.0), which was already in the installed tree, so the lockfile adds no package. The daemon package exports two more entry points, ./composer-prompts and ./workflow-scope. The Node requirement is unchanged (node >=22). Install scripts are unchanged: the package's only lifecycle script is still postinstall: node scripts/check-abi.mjs.

    #1481, #635, #1273 · thanks @Mr-Neutr0n, @AdamWhitehurstLink

  • ChangedA daemon with its own OpenRig home but your real home folder now warns once and starts. A community contribution.

    A daemon with its own OPENRIG_HOME but the real HOME or CODEX_HOME writes one advisory line to daemon.log and starts anyway.

    #1299 · thanks @AdamWhitehurstLink

  • ChangedGetting started pins the rigs skill to your release, with separate Claude Code and Codex commands.

    Getting started pins the rigs skill to your installed release, with separate Claude Code and Codex commands and a Linux note for Codex's sandbox.

    #1431Link

  • ChangedThe README now says only the older web UI is in maintenance mode. Reported by a community member.

    The README says only the older web UI is in maintenance mode.

    #1491 · reported by @jethrolarsonLink

  • ChangedRepository checks run on every push to main, and shipped skills come from one source. A community contribution.

    The Linux checks run on pushes to main; shipped skills regenerate from one home in the repository; a daemon-restart scenario joins the installed-package checks; and the snapshot tick looks up its restore source only when a seat changed.

    #1487, #1396, #1440, #1375 · thanks @DeryFerdLink

  • FixedA custom permission policy saved with Windows line endings now takes effect instead of falling back to the default. A community contribution.

    A custom permission policy saved with Windows (CRLF) line endings now takes effect. It used to fail to parse, so the seat fell back to the advisory floor; now it resolves to its declared posture at the next launch or restore.

    #1402 · thanks @rudycelekliLink

  • FixedAgents launch even on systems missing the usual rm command. A community contribution.

    The temporary launch script removes itself with /bin/rm or, if that's missing, the shell's own rm, so the agent still launches under set -e.

    #1310 · thanks @haralezLink

  • FixedCodex sign-in is found even with HOME unset, and an empty OPENRIG_HOME counts as unset. A community contribution.

    With HOME unset, rig auth and the daemon look for Codex sign-in files in the account's real home. An exported but empty OPENRIG_HOME is treated as unset by the TUI's socket, the terminal token lookup and rig crash-cart.

    #1418, #1470 · thanks @DeryFerd, @rudycelekliLink

  • FixedTests are cleaner and pass on macOS's temporary folder. A community contribution.

    Tests use stub runtimes, clean up their temporary folders, keep compaction packets out of the shared folder and pass on macOS's temporary folder.

    #1298, #1300, #1352, #1362, #1330 · thanks @AdamWhitehurst, @shravansumanthananLink

  • FixedTiming-sensitive tests are steadier, and transcript tests run in parallel again. A community contribution.

    Timing-sensitive tests wait on conditions; the native transcript suite runs concurrently again; cross-host usage gains tests; and two repository scripts were fixed.

    #1245, #1255, #1427, #1443, #1447, #1377, #1265, #1229, #1230 · thanks @sn1thy, @rudycelekliLink

Known issues: 20 for this release. Read them
  • On a Mac with more than one user account, a second user's rig commands can reach the first user's OpenRig. In the first-user check, the second person's ordinary commands reached the first person's daemon on its default port (7433), read one of its queue rows and sent a request to the first person's operator, which ran its checks and refused to work on the other user's private project. Running each user's daemon on its own port let both people work, but it doesn't keep them apart. The code involved matches 0.6.11's; 0.6.11 wasn't run to compare. It's being diagnosed for 0.6.13.
  • Managed compaction failed in two of six runs on this release. In one, saving the agent's recap needed a one-off approval, so the agent stopped at the approval and the compaction was never sent. In the other, the restore map was ready about ten seconds after the 120-second preparation deadline, so the compaction wasn't sent. The code involved matches 0.6.11's; 0.6.11 wasn't run to compare. Confirm that a compaction ran as described in the next item.
  • After a compaction, refocus may not show the agent's current work. For active work, its trace can time out and report a gap; for parked work, it can show a general fallback. The code involved matches 0.6.11's; 0.6.11 wasn't run to compare.
  • The one full snapshot restore run on this release reported partially_restored: the three seats meant to be running came back, and a deliberately stopped seat was left awaiting a decision.
  • Managed compaction's command budget is 600 characters, set from one comparison on Claude Code 2.1.282 (792 characters ran as a command, 850 didn't), and a later Claude Code could move that line. Nothing confirms compaction ran; read submitted, unconfirmed as reached, and confirm by the restore request or the drop in context (#1483).
  • Two plugin hook runs for the same seat aren't serialized: if a harness overlaps them, a post-compaction record can be lost or a refocus delivered twice. Overlapping runs weren't tested, and the samples that showed no prompt stall don't show that overlaps or stalls can't happen (#1344, #1475).
  • rig policy current and plain rig ps don't show a policy stored with rig policy apply --seat; rig seat status and pod-aware export do (#1285).
  • env: and --env values aren't secret, and members added later with rig grow can't carry a member-level env: (#1294).
  • rig up --env is not forwarded for flat-node specs or v1 bundles, although the launch may succeed. Do not rely on the flag for those formats in this release (#1294).
  • A fresh handover of a Claude seat in the classic renderer can report complete before the new Claude is ready, because the readiness check can match the previous occupant's text still in the pane, so the handover packet may be typed before the successor starts. 0.6.11 has the same behaviour. Until it's corrected, check that the successor read its packet (#1544).
  • One Slack app across machines was simulated in one process, never run on two real machines. Relayed events are trusted from the calling daemon, a relay that keeps being refused is retried with no limit, rig slack verify on the hub doesn't check relayed channels, and an answer from a seat other than the one the message reached still posts at the top level (#1436).
  • The draft-aware typing guard waits for idle inside the seat's delivery lease when the input box is empty, which can delay other work for that seat (not measured), and it can't guard text a person types in the instant before OpenRig types (#1481).
  • A Claude account's availability always reads unknown with usage windows on, until a seat's reading can be linked to its login (#1504).
  • A restore starts seats one after another, so each seat that never draws its screen adds about the readiness timeout (#1359).
  • A delivery already in transport when its watchdog stops still completes, with its records (#1325).
  • The recent-activity index costs about 10 to 12 MB on a long-running install, and each new transition writes one more index entry (#1326).
  • The openrig-user skill's subscription section mentions apps that don't ship in this release; don't look for them (#1450).
  • With bundle.services_enabled on, rig up <file>.rigbundle installs into the current folder when you don't give --target (#1474).
  • A send to a seat can still be refused for a quoted permission prompt that isn't really waiting; this is unchanged from earlier releases.
  • Carried from 0.6.11:
    • rig seat restart --keep-conversation supports Linux only, and its native result hasn't been re-run on 0.6.12.
    • The rig status API can call a running rig blocked because of one seat that isn't running: it folds a restore forecast into current status (#1141).
    • A Codex seat can keep reading as at its usage limit in a constructed screen case that hasn't been seen in a real session (#1185).
    • After rig scope slice create says it couldn't verify membership, the slice was kept. Check mission.yaml before creating it again (#1007).
    • The first-install check is still limited: on this release it ran on a Mac that had been used before, with fresh user accounts, for Claude Code and Codex (see How it was tested). A brand-new Mac and native Windows haven't been checked, and Linux was last checked with 0.6.11.
    • A second session in the same folder can misread a running team; the operator can point a person without a display at the shared dashboard without saying how to open it; the skill installer may not select Claude Code when it detects another agent; rig doctor checks both harnesses; rig tui --shared attaches on the default tmux server; a team's first steps can still ask for approval; a seat waiting at a permission prompt shows no product notice of its own; a launched team writes into its working folder; a resumed Claude seat can't be confirmed after /clear, an in-process /resume or a hand-started process; Codex team seats don't ask before lifecycle commands; the send gate trusts the latest recorded hook; and after a restart rig status shows Kernel: skipped.
    • A Claude Code seat whose permission request was approved automatically can still read "needs input"; the Codex case is fixed (#943, #896).
    • Slack missed-message recovery covers the default channel only, and private channels and direct messages aren't supported targets.
    • Older issues, as in 0.6.11: the starter's Codex reviewer needs a Codex newer than 0.145; a restore can report a problem with a seat that works (#273); a claude alias defined only in a nushell rc doesn't resolve; after a reboot, start the daemon with rig daemon start and bring your rig back with rig up <name> --existing; the web UI's file preview runs scripts, so preview only files you trust; browser access isn't complete browser isolation; and Codex network inside the sandbox hasn't been checked with real logins, managed policy bundles or on Linux.
OpenRig 0.6.11Idle agents aren't woken twice for the same work, and forked conversations get their own session.7 added2 expanded13 changed20 fixed

19 contributors · Release notes

Highlights

  • FixedAn agent that has set work aside is no longer woken again and again for tasks that haven't changed.

    A parked seat whose occupant is known isn't woken again for the same rows after a wake was delivered, until it updates one of them or one changes state. A failed, refused or unrecorded wake still repeats at the next park, and a new occupant gets its first wake. "Delivered" means the wake was typed into the seat's terminal, not that the agent read it.

    #1142Link

  • ChangedA message that waits for an agent to go idle no longer holds up every other message to that agent. A community contribution, fixing a community member's report.

    rig send --wait-for-idle N waits before it takes the seat's delivery lease, so other sends and queue wakes to that seat aren't held behind a long wait. N is now a deadline from the start of the wait, including any time spent waiting for the lease. A timeout names the wait you asked for.

    #1103, #1183 · thanks @lab1207 · reported by @z4ccLink

  • ChangedBringing a team back now stops and asks when an agent's earlier conversation might still be resumable, instead of starting it over. A community contribution.

    Restore no longer starts a seat fresh when an earlier occupant left a resume token. If a seat wasn't running when the snapshot was taken, but an earlier session recorded a resume token, rig up --existing and rig launch stop that seat at awaiting-decision and start nothing, because the token doesn't prove that conversation can still resume. rig launch of such a seat now exits 1 where it used to start it fresh. The message names the command that starts it fresh on purpose. For a seat stopped when the snapshot was taken, restore does not resume an earlier recorded conversation; the offered --fresh command starts a new conversation, not that recorded one.

    The status API for a rig, GET /api/rigs/:id/status, can call a running rig blocked because of one such seat: it folds the restore forecast into the rig's status, though no seat is halted. rig status and the TUI's rig list don't show it for a running rig, and the web UI's "Resolve & restore" still works.

    #1141 · thanks @haralezLink

  • FixedA Codex agent that hits its usage limit now stays marked as limited, instead of looking like it's working. A community contribution, toward two community members' reports.

    A Codex seat at its usage limit stays unknown with reason usage_limit while its screen redraws, instead of reading running, and rig ps --nodes shows usage_limit under REASON. It clears when a readable screen shows no banner, or when Codex shows it's working again.

    A Codex seat can keep reading as at its usage limit when an old banner is followed by a submitted prompt and the agent's reply, with no Codex working line and no input line below. The case was constructed from the source and hasn't been seen in the real sessions reviewed.

    #1185 · thanks @XTLine · reported by @Jejugo, @supercu00Link

  • AddedOn Linux, a Codex agent can be restarted in its own pane on the same conversation, for example after its account's limit resets.

    Restart a Codex seat in place, on Linux. rig seat restart <seat> --keep-conversation --reason "<why>" restarts one Codex seat in its own pane on the same conversation, so it starts again on whatever account its Codex home now holds. It doesn't switch accounts itself. Before it stops anything, it checks that the seat is a Codex seat OpenRig launched, in a single pane, with a conversation it can prove, and that relaunching wouldn't change the running settings; any doubt refuses with nothing stopped. --plan runs every check and stops nothing. --verify --expect-account <account> reports moved only when a tool turn has completed in the same conversation since the restart and Codex's status names that account.

    Linux only: on macOS, a request that gets as far as reading the running process refuses before stopping the seat. It has restarted one real Codex seat (Codex 0.153.4), doesn't verify which account the seat resumes on, and wasn't tried with Codex builds that share one app server.

    #1196, #1195, #1212, #1361Link

Also in this release 37

Seats & restore 6

  • AddedBringing a team up now warns you when it picked the root folder to launch in. A community contribution, finished here.

    rig up warns on stderr when it chose / as the launch folder itself.

    #1150, #226 · thanks @Marius-progLink

  • ChangedStarting an agent fresh now checks before it stops anything, and can preview what it would do. A community contribution, toward a community member's request.

    rig seat launch --fresh --stop checks before it stops anything. A seat with a still-live older session is refused before the current agent is stopped; 0.6.10 stopped it first. --plan previews a fresh launch without changing anything and exits 0 even when it would be blocked. --reason is required only to execute; leaving it out reports missing_reason.

    #1156 · thanks @XTLine · reported by @some-marketingLink

  • ChangedAn agent you stop on purpose no longer makes its team look degraded. A community contribution, fixing a community member's report.

    A seat you stop on purpose no longer makes its rig read degraded. rig seat stop records the stop, rig ps and the TUI leave that seat out of the rig's state, and running counts still exclude it. rig ps --nodes --json carries intentionallyStopped. A rig whose seats were all stopped this way reads stopped.

    #1192 · thanks @Aschenbath · reported by @aanestesiaLink

  • ChangedWhen an agent's conversation is really gone, a restore now stops and asks instead of reporting a failure. A community contribution.

    In a restore of a rig whose seats are in pods, a seat is rolled back as unresumable only when its runtime reports the conversation missing. When Claude, Codex or Pi reports that, the restore rolls the seat back to awaiting-decision and starts nothing, instead of reporting a failed launch and leaving the new pane behind. A rig where every seat ends this way reads partially_restored instead of failed; the exit code is 1 either way. A Claude that exits to its shell for another reason keeps 0.6.10's result: the restore reports the seat failed and keeps its pane, so you can read what happened. Restores of rigs without pods keep their earlier handling.

    #1191, #1218 · thanks @duncanleungLink

  • FixedAgents no longer inherit the identity of the Claude Code or Herdr session that launched them. A community contribution, finished here.

    Seats no longer inherit the launching Claude Code or Herdr session's identity variables, such as CLAUDECODE. If removing them fails, the launch goes ahead with a warning.

    #1151, #771 · thanks @adampogLink

  • FixedA slow readiness check no longer overwrites a newer launch. A community contribution.

    A late readiness result no longer overwrites a newer launch attempt.

    #1188 · thanks @XTLineLink

Queue & messaging 9

  • AddedA new setting, off by default, makes queue commands print a short receipt: line instead of the whole task.

    New switch, off by default: output.compact (or OPENRIG_OUTPUT_COMPACT). The seven queue write commands (rig queue create, claim, unclaim, update, block, handoff and handoff-and-complete) print a short receipt instead of the whole row, and --full prints the whole row. While it's off, their output is unchanged; --full is accepted, and rig config lists the key.

    #1137Link

  • AddedCreating a task for a person now reports whether it was posted to their Slack, beside the terminal wake-up. A community contribution.

    rig queue create --verify to a registered person who is also a seat with a pane reports the Slack receipt beside the terminal wake, in a gateway object (posted, transport-failed, never-posted or still-pending). Posted isn't read. GET /api/queue/:qitemId returns ownerNotificationLevel.

    The wait is bounded by the existing 30-second default, and it can use all of it even when Slack isn't set up or the row won't be posted; the Slack side then reads still-pending. The 30-second wait wasn't tested on the exact package.

    #1085 · thanks @rem4ik4everLink

  • ChangedAsking for an agent's work candidates now returns up to 50 held and 50 next tasks, and says when either list was cut.

    rig queue whoami --work-candidates now returns up to 50 held and 50 next rows, with heldTruncated and nextTruncated; heldAndNextTruncated now means either list was cut. With OPENRIG_REFOCUS_WORK_PACKET on (off by default, as in 0.6.10), the refocus hook's work packet lists held and next work separately, up to 50 each.

    #1066Link

  • ChangedCreating a task with verify now reports a claimed task as claimed, fixing a known issue from 0.6.10.

    rig queue create --verify reports outcome: "claimed" for a claimed row whose wake wasn't confirmed, instead of indeterminate. This was a known issue in 0.6.10.

    #1168Link

  • FixedVerified messages now confirm long messages that the agent's screen indents. A community contribution.

    rig send --verify confirms enveloped multi-line messages that the agent's screen indents, and queue wakes use the same check.

    #1145 · thanks @haralezLink

  • FixedA handed-off task with no visible next agent now gets flagged, just like a finished one. A community contribution, toward a community member's request.

    A handed-off closure with no visible successor gets the same custody advisory and stuck-sweep finding as a done closure.

    #1189 · thanks @XTLine · reported by @m3ac-AllbrittenJLink

  • FixedBad chat messages now get a request error instead of a server error. A community contribution.

    The chat send and topic routes return 400 before storing anything for payloads that used to fail with 500.

    #1122 · thanks @rudycelekliLink

  • FixedA wake request with a malformed generation now gets the usual reply. A community contribution.

    /api/wake-resolve answers a fractional or non-numeric generation with its usual "does not exist" reply.

    #1129 · thanks @rudycelekliLink

  • FixedWatchdog setup refuses a scan interval that isn't a number. A community contribution.

    Watchdog registration refuses a scan_interval_seconds that can't be turned into a number, such as non-numeric text, a boolean or an empty array.

    #1131 · thanks @rudycelekliLink

Claude 2

  • FixedA forked Claude agent now gets its own conversation ID, so OpenRig can confirm it when bringing it back.

    A forked Claude seat (rig fork, or session_source: fork) launches with its own session ID, so strict restore and clear-attention can verify it as its own conversation.

    Forking a Claude seat needs Claude Code 2.0.73 or later, which OpenRig doesn't check. Forks launched before this keep reading mismatch until they're relaunched.

    #1144Link

Codex 2

  • AddedA new setting, off by default, lets OpenRig read a Codex login's usage windows when you ask it to.

    New switch, off by default: provider.usage_windows (or OPENRIG_PROVIDER_USAGE_WINDOWS in the daemon's environment). rig provider status --refresh reads a Codex login's usage windows once. While it's off, --refresh says how to turn it on and exits 1.

    #1194Link

  • Addedrig whoami now shows a Codex agent's conversation ID once it's confirmed resumable. A community contribution, toward a community member's request.

    rig whoami --full --json shows a Codex seat's runtimeContext.threadId when its stored conversation ID was verified resumable.

    #911 · thanks @Coder8124 · reported by @mgall-ibizdigitalLink

Pi 1

  • ChangedWhen a Pi or OMP turn fails, you now see the provider's own reason. A community contribution.

    A failed Pi or OMP turn shows the provider's own reason when it gives one.

    #1181 · thanks @smotaLink

Slack 1

  • FixedA Slack reply also sent to the channel is no longer lost when the connection drops. A community contribution, fixing a community member's report.

    A Slack reply sent with "Also send to channel" in the default channel is recovered after a connection gap.

    #1187 · thanks @XTLine · reported by @z4ccLink

TUI 2

  • ChangedThe TUI now says when its queue counts are incomplete, instead of showing them as exact.

    The TUI says when a queue sample hit its cap or failed to load: counts read N+, a seat missing from the sample shows ?, and Pulse no longer lists a NEEDS YOU item a second time.

    The caps count the whole host, so a quiet rig can read ? while another rig is busy.

    #1175Link

  • FixedThe TUI Topology table's queue, work and activity columns fill again. A community contribution.

    The TUI Topology table's Q, WORK and NOW columns fill again on drilled views and on a seat's page. They had been empty there since 0.5.14.

    #1173 · thanks @Quentin-MLink

CLI & hosts 3

  • ChangedThe docs were updated for 0.6.11.

    The what-changed note, capability map and changelog were written for 0.6.11.

    #1253Link

  • FixedThe team list and the agent list now count running agents the same way. A community contribution.

    rig ps takes a rig's running count and status from the same set of sessions as rig ps --nodes.

    #1186 · thanks @XTLineLink

  • FixedOpenRig finds agents running in panes it doesn't manage by their exact process names. A community contribution.

    Discovery of unmanaged panes matches agent process names exactly, plus claude.exe and names cut to 15 or 16 characters.

    #1133 · thanks @rudycelekliLink

Specs & bundles 3

  • ExpandedA seat's folder in a rig spec can now use ~ and environment variables. A community contribution.

    A member's cwd in a rig spec can be ~, start with ~/, or use $VAR or ${VAR}, expanded from the daemon's environment, when the path as written doesn't exist.

    #1153 · thanks @Quentin-MLink

  • ExpandedProof commands can now be pointed at a project by name. A community contribution, finished here.

    rig proof show and rig proof judge take --project <id> or a <project>: scope prefix, resolved through the workspace catalog. Scope readiness for a project selected in the TUI uses that project's own root.

    #1149, #136 · thanks @korallis, @dajiaohuangLink

  • FixedCreating several scope slices at once no longer gives two of them the same number. A community contribution.

    Parallel rig scope slice create calls get different slice numbers. A number is never reused, and each create leaves a hidden slices/.nn-NN claim file.

    After rig scope slice create says it couldn't verify membership, the slice was kept. Check mission.yaml before creating it again: creating it again makes a second slice with the same name.

    #1007 · thanks @rudycelekliLink

Context & skills 2

  • AddedA new reference page shows how to keep a watch for a person with today's queue commands.

    A reference page on keeping a watch for a person with today's queue commands.

    The page says a timer fires once, but a held-back wake uses up that fire: when the typing guard holds a one-shot --wake-after wake back, the timer isn't retired and can wake the owner again at each interval. Read the task's transitions after each wake.

    #1064Link

  • ChangedThe rigs and openrig-skills skills now say clearly which one is for a person and which is for an agent. A community contribution.

    The rigs and openrig-skills skill descriptions split by who is asking: a person in their own session, or an agent inside a rig.

    #1174 · thanks @ehnruizLink

Setup & platform 6

  • ChangedAfter upgrading the CLI, restart the daemon so it runs the new version. One small database change runs on the first start and leaves your data as it is.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. One database migration runs on the first start: 103 adds one column to sessions, intentionally_stopped, which is 0 for every existing row, so OpenRig can tell a seat you stopped on purpose from one that exited. There are no migrations 100 or 102. The bundled openrig-core plugin stays at 0.1.9; two of its files changed.

    #1192, #1174, #1066 · thanks @Aschenbath, @ehnruizLink

  • ChangedNo npm dependencies or install scripts changed, and the Node requirement is unchanged.

    No npm dependencies were added, removed or changed, and the Node requirement is unchanged (node >=22). OpenRig's own version fields advance to 0.6.11. Install scripts are unchanged: the package's only lifecycle script is still postinstall: node scripts/check-abi.mjs. The one database change is migration 103.

    #1253Link

  • FixedOpenRig refuses a daemon port that can't exist, with a clear message. A community contribution.

    rig config set daemon.port refuses a port outside 0–65535, and a port like that from the environment or config.json falls back to the file or default with a warning. rig daemon start --port refuses one too, with a clear message and exit 1.

    #1140, #1201 · thanks @DeryFerd, @Coder8124Link

  • FixedTests that failed on some Linux machines now pass there. A community contribution, finished here.

    Daemon and CLI tests that failed on some Linux machines (ext4 inode reuse, dash as /bin/sh, a 002 checkout umask) pass there now.

    #1148, #83 · thanks @mvdpoelLink

  • FixedTwo test fixes, for cleanup and for macOS. A community contribution.

    The pane-isolation tests clean up after themselves, and the TUI default socket-path test no longer fails on macOS.

    #1169, #1182 · thanks @shravansumanthananLink

  • FixedThe portability report runs from a symlinked path. A community contribution.

    The portability report runs when it's started through a symlinked path.

    #1109 · thanks @rudycelekliLink

OpenRig 0.6.10Set up with only the providers you have, with rig setup --providers claude, codex or both.4 added1 expanded13 changed26 fixed

11 contributors · Release notes

Highlights

  • AddedTell setup which agent harnesses you use, and it installs and checks only those. A harness you skip no longer shows up as a failure.

    Setup asks only about what you use. rig setup --providers claude (or codex, both, or a comma list) installs and checks only the harnesses you chose. One you didn't choose reads skipped, never failed. Before, a person who used only Claude Code saw Codex checks fail. The first hour also stops showing tmux's "error connecting to …" when the daemon starts, and the next steps say the remaining steps are part of the install, not extras.

    rig doctor still checks both harnesses, including one you don't use. rig setup --providers doesn't change it.

    #1065Link

  • FixedA Claude agent that resumes under a new conversation ID now comes back confirmed instead of needing your attention. A community contribution.

    A resumed Claude seat whose session ID changed now proves. Claude can continue --resume under a new conversation ID. When the first SessionStart hook from the process OpenRig launched reports that resume, OpenRig records the new ID. The seat restores as resumed, and sends stop warning that its identity can't be confirmed. Before, such a seat stayed attention_required.

    A resumed Claude seat still can't be confirmed after /clear, an in-process /resume, a hand-started process or a launcher shim, or with a plugin older than 0.1.9.

    #1080 · thanks @haralezLink

  • FixedMessages and queue wake-ups now reach Codex agents started through a launcher. Reported by a community member.

    Codex seats behind a launcher: a seat whose codex is a launcher that starts Codex as a child now receives rig send and queue wakes. Before, every send was refused with "reports sh as the foreground command". This had been broken since 0.5.17.

    #1088 · reported by @donatoazLink

  • FixedThe attach commands OpenRig prints now find your agents when the daemon runs on a non-default tmux server.

    Attach commands name the right tmux server. If the daemon was started inside tmux on a non-default socket, every attach command it prints now carries -L <name> or -S <path>. From inside tmux, run it as env -u TMUX <command>. This was 0.6.9's known issue about attach commands reporting "no sessions".

    rig tui --shared still attaches on the default tmux server, so it can't find the dashboard when the daemon runs on a non-default tmux socket. Use rig tui there instead.

    #1083Link

Also in this release 40

Seats & restore 6

  • ChangedLaunching an agent that has exited no longer says it's already running. It says the agent needs attention and how to bring it back.

    rig launch no longer calls an exited agent running. On a seat whose agent exited to a shell in its kept pane, rig launch <rigId> <seat> returns attention_required and exits 1, with the ways back. It used to report the seat already running.

    #1070Link

  • ChangedBringing a rig back now says so when an agent is missing part of its guidance, instead of reporting a full restore.

    rig up <rig> --existing reports a seat still missing part of its guidance. The rig then reads partially_restored instead of fully_restored, and the command exits 1.

    #1068Link

  • FixedBringing a rig back now restores the OpenRig guidance that taking it down removed, and leaves your own text alone.

    rig up --existing puts back the OpenRig guidance that rig down removed from CLAUDE.md, CLAUDE.local.md or AGENTS.md. This happens before a resumed seat starts, and the person's own text isn't touched. Before, the seat came back without its role and culture guidance while the restore read fully restored.

    #1068Link

  • FixedA restore no longer takes a launcher's word for which conversation is running, so it can't report a false resume.

    A restore no longer trusts a launcher's word. A launcher that isn't Claude can name one conversation while the Claude it started runs another. That restore now reads attention_required instead of a false resume.

    #1091Link

  • FixedAn agent whose terminal session is gone now reads as detached, with the way to bring it back. A community contribution.

    A seat whose tmux session is confirmed gone reads detached, and rig ps --nodes says to restore or relaunch it. Before, it read as needing attention and could still look active.

    #1074 · thanks @xwcqLink

  • FixedStarting OpenRig now says why it skipped an existing kernel and how to bring it back. A community contribution.

    rig start says why it skipped an existing kernel and how to bring it back.

    #1060 · thanks @haralezLink

Queue & messaging 9

  • AddedA new setting keeps agent-to-agent escalations out of your Slack unless a task is addressed to a person. A community contribution, toward a community member's request.

    New escalation setting: queue.wake_human_rung defaults to always. Set it to explicit-only to keep agent-to-agent escalations off the person's Slack unless the row is addressed to a person.

    #1090 · thanks @Coder8124 · reported by @a4w-h4yLink

  • ChangedThe short queue list now shows each task's summary, and leaves out empty fields instead of printing them blank.

    Compact rig queue list rows carry summary, and so do overdue and undelivered. The fields they leave out are now absent instead of null or "", and fieldsElided names them.

    #1096Link

  • ChangedA task an agent has claimed now reads as claimed even when its wake-up wasn't confirmed. A community contribution, fixing a community member's report.

    lastNudgeResult reads claimed on a claimed row whose wake wasn't confirmed. The recorded value is kept in the new lastNudgeWireResult.

    #1094 · thanks @Coder8124 · reported by @roALAB1Link

  • ChangedChatroom history now shows the newest messages by default, so a long room no longer opens on its oldest. A community contribution.

    rig chatroom history returns the newest messages when you give neither --after nor --since, still listed oldest first. Before, a long room returned its oldest.

    #1057 · thanks @jayhemnani9910Link

  • ChangedCreating a task with verify now reports the wake-up and pickup as soon as they happen, instead of waiting 30 seconds. A community contribution, toward a community member's request.

    rig queue create --verify reports an agent seat's wake result and any claim as soon as one is recorded. Before, it waited 30 seconds and said still-pending.

    It can report outcome: "indeterminate" for a row the seat already claimed. Read claim for pickup: neither the claim nor this outcome shows the message was displayed or read. It isn't a failed handoff, so don't re-run the create.

    #1029 · thanks @rem4ik4ever · reported by @d3fvxlLink

  • FixedA rig name with an underscore or percent sign in it now filters views exactly. A community contribution.

    _ and % in a rig view show <lens> --rig <name> rig name are no longer wildcards, in all seven lenses that filter by rig.

    #1126, #1165 · thanks @rudycelekliLink

  • FixedSearching chat for a keyword like config.json or C++ now matches it exactly. A community contribution.

    rig ask matches chat keywords such as config.json or C++ literally.

    #1127 · thanks @rudycelekliLink

  • Fixedrig heartbeat reads queue files with Windows line endings, and picks its latest proof correctly on hosts not set to UTC. A community contribution.

    rig heartbeat reads queue files with Windows line endings, and picks its latest proof correctly on a host not set to UTC.

    #1120, #1121 · thanks @rudycelekliLink

  • FixedQueue recovery lookups no longer scan every task in the queue.

    The queue's recovery lookups no longer scan every row.

    #1073Link

Claude 1

  • FixedA message to an idle Claude agent is no longer held back by the faint suggested prompt in its input box.

    Claude's faint suggested prompt in an empty input box no longer reads as a person's draft, so a send to that idle seat goes through. Real typed text is still protected.

    #1139Link

Codex 3

  • ChangedA Codex agent that has hit its usage limit no longer reads as idle. A community contribution, toward a community member's request.

    A Codex seat showing its usage-limit banner reads unknown with reason usage_limit instead of idle, and rig provider signals can show a provider-event signal for that seat's account that allows a switch decision.

    #973 · thanks @lab1207 · reported by @JejugoLink

  • FixedA Codex agent's context reading no longer disappears after a quota-only usage record. A community contribution.

    A Codex seat keeps its last context reading across quota-only usage records.

    #1124 · thanks @rudycelekliLink

  • FixedA fresh Codex launch keeps git paths that end in a space. A community contribution.

    A fresh Codex launch keeps git metadata paths that end in whitespace.

    #1134 · thanks @rudycelekliLink

Slack 1

  • AddedA Slack decision button that doesn't count now gets a reply in the thread saying why.

    A Slack decision click that isn't recorded now gets one reply in the thread saying why. It covers clicks from someone who isn't registered, clicks on a decision sent to someone else or no longer waiting, and buttons that no longer match. A recorded click still gets its usual reply. It's best effort and needs the Slack bot token.

    #1067Link

TUI 1

  • FixedFour small TUI fixes for keyboard input, emoji, paging and opening files at a heading. A community contribution.

    The TUI counts CR+LF as one Enter, keeps an emoji whole at a wrap, pages Local reading directories by 10, and skips fenced examples when opening a file at a heading.

    #1111, #1112, #1113, #1114 · thanks @rudycelekliLink

CLI & hosts 12

  • ExpandedYou can add to a rig by its name as well as its ID. A community contribution.

    rig add takes a rig's name as well as its ID.

    #1027 · thanks @rem4ik4everLink

  • ChangedCapturing the last N lines of an agent's terminal now gives you exactly those lines. The old output is still there behind a flag.

    rig capture --lines N shows the last N lines. When earlier lines are cut, stderr says how many. In --json, lines is then the count returned, and requestedLines and omittedLines are new. For the old output, N history lines plus the whole pane, add --history-plus-pane, which also keeps the old JSON without those two fields. Without --lines, nothing changed.

    #1136Link

  • ChangedOpening terminals now uses Herdr, or plain tmux when Herdr is missing, never cmux. Reported by a community member.

    When a caller of the daemon's terminal API names no provider, the daemon uses cmux if Herdr isn't available, and says so. rig terminal open without --provider, and the TUI's "Open terminals", open Herdr, or plain tmux when Herdr is missing, never cmux. The TUI's preview now asks for the same provider as the window it opens, so it isn't refused when cmux is running.

    #1071, #1167 · reported by @R14014Link

  • ChangedThe docs were updated for 0.6.10.

    The what-changed note, capability map and changelog were written for 0.6.10.

    #1166Link

  • FixedOpenRig recognises a tmux session started inside a Herdr pane. A community contribution.

    A tmux started inside a Herdr pane is recognised by Herdr's own markers.

    #1130 · thanks @AdamWhitehurstLink

  • FixedA limit that isn't a number now gets a request error instead of a server error. A community contribution.

    A ?limit= that isn't a number returns 400, not 500.

    #586 · thanks @Coder8124Link

  • FixedUsage commands print errors properly in JSON and read every sample in their window. A community contribution.

    rig usage top|series --json prints the daemon's error as JSON, and rig usage top reads every sample in its window.

    #1075, #1116 · thanks @oodadoudou, @rudycelekliLink

  • FixedCreating a workflow now prints what it made. A community contribution.

    rig workflow instantiate and project print the instance and packet they made.

    #1102 · thanks @jayhemnani9910Link

  • FixedFollowing a transcript keeps lines that end in a percent sign. A community contribution.

    rig transcript --tail keeps a line ending in %.

    #1104 · thanks @oodadoudouLink

  • FixedA --json written after -- no longer turns an error into JSON. A community contribution.

    --json after -- no longer turns an error into JSON.

    #1106 · thanks @rudycelekliLink

  • Fixedrig env prints the daemon's error instead of a JavaScript one. A community contribution.

    rig env prints the daemon's error instead of a JavaScript one.

    #1115 · thanks @rudycelekliLink

  • FixedReading a large file no longer cuts a character in half. A community contribution.

    A file read over 1 MiB ends at a whole UTF-8 character.

    #1119 · thanks @rudycelekliLink

Specs & bundles 2

  • FixedScope and progress files are updated only where they should be, and examples in them are no longer mistaken for real sections. A community contribution.

    Scope and progress: progress rows go only under a matching ## heading, frontmatter updates stay inside the exact --- delimiters, a capability delta expires only with a readable successor file, and fenced examples no longer count as slice sections or progress tasks.

    #1107, #1110, #1123, #1125, #1128 · thanks @rudycelekliLink

  • FixedInstalling a package finds the end of a guidance block reliably. A community contribution.

    rig package install looks for a guidance block's closing marker only after its opening one.

    #1135 · thanks @rudycelekliLink

Context & skills 1

  • ChangedTeams are guided to need fewer approvals, to say what a launch changes in your folder, and to tell you when an agent is waiting on you.

    Teams are guided to ask less and say more. Starter and factory guidance now directs teams toward first steps and checks that need fewer approvals. The operator is instructed to explain what a launch changes in your project folder and to offer a separate copy before launch. Operators and leads are instructed to surface a waiting seat's prompt and attach command.

    The first-user check still needed four team approvals and didn't surface the reviewer's prompt until the person asked.

    #1082, #1086, #1087Link

Setup & platform 4

  • AddedNew tests and repository checks. A community contribution.

    Tests and repository checks: a scenario for the rig up round trip; the docs guard keeps unusual file names exact; the portability report handles header-shaped added text; and GET /api/bootstrap lists same-second runs newest first.

    #1092, #1105, #1108, #1132 · thanks @DeryFerd, @rudycelekliLink

  • ChangedAfter upgrading the CLI, restart the daemon so it runs the new version. Two small database changes run on the first start and leave your data as it is.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. Two database migrations run on the first start, and neither changes existing data: 099 adds one partial index to the queue table, so the queue's recovery and stuck-sweep lookups stop scanning every row, and 101 adds four empty columns to sessions, so OpenRig can remember a resumed Claude conversation's new ID. There is no migration 100. The bundled openrig-core plugin goes from 0.1.8 to 0.1.9.

    #1073, #1080 · thanks @haralezLink

  • ChangedNo npm dependencies or install scripts changed, and the Node requirement is unchanged.

    No npm dependencies were added, removed or changed, and the Node requirement is unchanged (node >=22). OpenRig's own version fields advance to 0.6.10. Install scripts are unchanged: the package's only lifecycle script is still postinstall: node scripts/check-abi.mjs.

    #1164Link

  • FixedOn WSL2, the first daemon start no longer refuses a free port after a slow check.

    On WSL2, a first rig daemon start after a timed-out probe goes ahead when the port is free. It's refused only when the port is really held, and the refusal names --port.

    #1061Link

OpenRig 0.6.9Typed Slack answers are kept and NixOS-installed Claude is recognised. Otherwise it's a quick fix release.2 added4 changed7 fixed

4 contributors · Release notes

Highlights

  • FixedWhen you answer a Slack decision in your own words, your reply is kept on the task instead of being lost. Reported by a community member.

    A typed Slack reply to a decision with structured questions is now kept on the row, in humanAnswers. Before, the decision closed with no recorded answer. The reply is placed under the first unanswered question and marked as typed, so text that matches an option's ID is never read as clicking it. The decision still closes, and closing doesn't mean approval.

    #1045 · reported by @AlexGhanemLink

  • ChangedA message sent to another machine that may have arrived now says delivery is unconfirmed instead of failed, with the check to run before sending again.

    A cross-host rig send --host to an http-registered host has a 30-second request budget, plus any --wait-for-idle time, instead of 5 seconds. If the answer doesn't come back, or the connection drops after the request went out, the send reads "Delivery UNCONFIRMED" (remote-outcome-unknown, exit 1) and tells you to check the target before any resend. Only a host that was never reached reads as unreachable.

    #1048Link

  • FixedA Slack connection that stays open but stops delivering is now noticed and replaced, and status says whether delivery is confirmed.

    OpenRig now notices a Slack Socket Mode connection that stays open while events stop, from Slack's server pings and from the echo of OpenRig's own posts, and replaces it: the new connection opens first, at most once every 5 minutes. rig slack status adds a Delivery: line beside "connected", and the connections view says whether delivery is confirmed.

    #1052Link

Also in this release 10

Seats & restore 2

  • AddedA refocus work packet is included, switched off, so nothing changes unless it's enabled.

    The refocus work packet is in this release, off by default: nothing changes unless it's enabled.

    #1043Link

  • FixedA kernel whose agents recovered from a failed start now reads ready, with the earlier failure still noted. Reported by a community member.

    A kernel whose first start failed and whose seats then recovered, for example after rig seat continue, now reads ready in rig status, with a separate line naming the earlier failure. Before, it kept reporting bootstrap_failed, and its agent list could show a seat twice.

    #1044 · reported by @rickjgardnerLink

Queue & messaging 1

  • FixedWaiting in a chatroom keeps going through a slow or restarting daemon instead of ending early.

    A long rig chatroom wait keeps waiting through a slow or restarting daemon instead of ending at the first failed poll: poll timeouts, connection refusals, and reset or closed connections are retried until --timeout. The first failure prints one line on stderr; other errors, such as a removed rig, still end the wait.

    #1047Link

Claude 1

  • FixedClaude Code installed from nixpkgs is recognised, so its agents read as running. A community contribution.

    Claude Code seats installed from nixpkgs are recognised as Claude and read running. Before, every one read attention_required. A seat that already carries an attention marker from an earlier failed launch keeps it until rig seat clear-attention.

    #1053 · thanks @haralezLink

Slack 2

  • AddedSlack status now shows how many incoming messages are waiting to be retried. A community contribution.

    rig slack status shows how many retained records for inbound messages, reactions and click answers are waiting to be retried; it counts records, not distinct messages. The backlog is kept across restarts, and if it can't be read, status says the count is unknown and why.

    #1036 · thanks @DeryFerdLink

  • FixedA Slack alert for a task that has already closed is no longer posted when the gateway restarts.

    A Slack alert whose first post failed is kept and retried when the gateway next starts; if its row has closed by then, the alert is no longer posted, and the row says why. Alerts for rows still open, decision-resolved notices and digests still post, and rig slack enable says how many earlier posts wait to be retried.

    #1051Link

CLI & hosts 2

  • ChangedThe docs were updated for 0.6.9, and now say that launching an agent takes the rig's ID, not its name.

    The what-changed note, capability map and changelog were written for 0.6.9, and they now say rig launch takes a rig ID, not a rig name.

    #1063Link

  • FixedApproving work for a named workspace now records the approval in that workspace, not the daemon's own, and a workspace with no missions folder is refused. A community contribution, fixing a community member's report.

    rig scope <tier> approve --workspace <path> now stamps the work tree you named. Before, it reported success while the stamp landed in the daemon's own work tree. If the named workspace has no missions/ folder, approve now refuses instead of stamping the configured one.

    #997 · thanks @xecanto · reported by @csaxton171Link

Setup & platform 2

  • ChangedAfter upgrading the CLI, restart the daemon so it runs the new version. One small database index is added.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. There is one database migration: 098 adds an index on (qitem_id, transition_id) to the queue's transition history, and a 0.6.8 daemon still opens the upgraded database. The bundled openrig-core plugin stays at 0.1.8.

    #1043Link

  • ChangedNo npm dependencies or install scripts changed, and the Node requirement is unchanged.

    No npm dependencies were added, removed or changed, and the Node requirement is unchanged (node >=22). OpenRig's own version fields in the package files and the lockfile advance to 0.6.9. Install scripts are unchanged: the package's only lifecycle script is still postinstall: node scripts/check-abi.mjs.

    #1062Link

OpenRig 0.6.8Preview a launch, on this machine or another, before anything starts. Most of the rest are fixes, many from the community.4 added10 changed8 fixed

10 contributors · Release notes

Highlights

  • AddedPreview what relaunching a single agent would do, including what happens to the others, before anything changes. A community contribution.

    rig launch <rig> <seat> --plan now previews a single agent's launch, as --seats already could: the snapshot it would use, the target, and what happens to the other agents, without launching anything. It works over --host too.

    #1023 · thanks @Totopo27 · reported by @some-marketingLink

  • FixedEditing one skill in the shared skill catalog no longer stops every agent's skills. Only that skill is skipped, with a warning, until you commit it.

    One skill being edited in the managed skill catalog no longer blocks every agent's skills. Before, any uncommitted or untracked file in the catalog made it unavailable, so rig context work-install, rig up, launch and restore preflight failed for every agent. Now that skill is skipped and named in a warning, the remaining clean skills stay available, and an agent's launch only warns. An agent that already has a copy of the skipped skill keeps it as it was, and the next applied projection can refresh it once the change is committed or restored. No agent receives uncommitted files.

    An uncommitted change to catalog.yaml itself still makes the whole catalog unavailable, because it changes what every selection means.

    #1031Link

  • FixedWhen a person replies inside a Slack thread OpenRig started, an agent's answer now goes to that same thread. A community contribution.

    When a person replies inside a Slack thread OpenRig opened, an agent's answer with rig queue create --human-intent update --reply-to <that reply's task> now posts in the same thread instead of as a new message. The messaging-the-human skill says how.

    Not tested with live Slack.

    #1021 · thanks @tianqizhao0704 · reported by @ivannovakLink

Also in this release 19

Seats & restore 4

  • ChangedA launch plan now checks the daemon's version first and won't send the plan to a daemon too old to understand it, which would launch instead.

    rig launch --plan reads the daemon's version first and refuses to send to a daemon older than 0.5.9, which would ignore the plan and launch.

    #1024Link

  • FixedIf a launch plan's answer shows the daemon actually acted, the command stops with an error and tells you how to check what happened.

    If the answer to rig launch --plan isn't a plan but shows the daemon acted, the command exits non-zero and tells you to check rig ps --nodes -A before retrying.

    #1024Link

  • FixedAn agent that goes quiet after compacting is still restored, instead of waiting until something wakes it.

    After a managed /compact, a Claude agent that takes no turn is still restored: the turn boundary, the restore request and the read-depth audit now reach it. Before, they waited for the agent's next turn, so an agent with nothing to do could sit unrestored until something woke it. Each step still waits until the agent's screen shows it idle, and only a fresh usage reading can start a compaction.

    Not tested with a real compaction.

    #1035Link

  • FixedShutting a team down still saves its recovery snapshot even if one agent's details can't be read. A community contribution.

    rig down still saves its recovery snapshot when finding one agent's resume details fails, instead of skipping the snapshot for every agent.

    #1030 · thanks @Vaishnavi220506Link

Queue & messaging 1

  • ChangedWhen an agent is woken for a task, it now sees the task's summary right away. A community contribution.

    When an agent is woken for a task handed to it, the reminder now shows the task's summary on one line, up to 120 characters, so it sees what the task is for.

    #1028 · thanks @rem4ik4everLink

Claude 1

  • FixedClaude agents started with Remote Control now confirm who they are instead of staying unconfirmed. A community contribution.

    A Claude agent launched with --remote-control confirms its identity instead of staying "identity not confirmed".

    #1025 · thanks @pr0xc3nt4ur1Link

Slack 2

  • AddedWhen Slack asks OpenRig to slow down for a few seconds, it now waits and tries the post once more instead of giving up right away. A community contribution.

    When Slack rate-limits a post and asks for a pause of 10 seconds or less, OpenRig waits that long and retries the post once. A longer pause is still left to the usual retry of retained messages.

    Not tested with live Slack.

    #1026 · thanks @DeryFerdLink

  • ChangedThe check that keeps the Slack bot token on Slack's own hosts now sits in the private-file download itself. A community contribution.

    The check that keeps the Slack bot token on Slack's own hosts now sits inside the private-file download itself, not only at its one caller.

    #1006 · thanks @DeryFerdLink

TUI 2

  • AddedIn the TUI, j and k now move up and down the list when the command line is empty. A community contribution, asked for by another community member.

    On an empty TUI command line, j and k move the selection down and up.

    Not tested in a live TUI session.

    #1019 · thanks @Totopo27 · reported by @pono-yviavantLink

  • ChangedA few TUI shortcuts moved to capital letters, so agents typing commands like find or mission into the TUI get the whole command through.

    TUI shortcuts that could swallow a typed command moved to capitals: the footer toggle from f to F, and in a selected Scopes view the mini-requirements and narrative keys from m and n to M and N. Agents drive the TUI by typing, so commands such as find, feed, mission, narrative and needs now reach the command line whole.

    Not tested in a live TUI session.

    #1020Link

Specs & bundles 4

  • AddedA new guide explains how to name a team's pods and agents.

    A topology naming reference explains how to name a team's pods and agents, from purpose to domain to role, and the rig spec, bundle and authoring guides point to it.

    #1000Link

  • ChangedWorkflow validation now catches a step that could never finish, instead of letting the workflow stall there later. A workflow that validated before may be refused now, with the step and the fix named. A community contribution.

    rig workflow validate now reports step_cannot_finish, and refuses to instantiate the workflow, when no allowed exit can finish a step or route onward. An allowed mapped exit is valid, and in a dependency graph handoff can finish a last step without a next one. Before, such a workflow passed validation and then stalled on that step.

    A spec that validated on 0.6.7 can be refused now. The message names the step and the fix.

    #1012 · thanks @tianqizhao0704Link

  • FixedScope audit accepts slice folders numbered 100 and up. A community contribution.

    rig scope audit accepts slice folders numbered 100 and above, which rig scope slice create makes after 99.

    #1016 · thanks @rudycelekliLink

  • FixedProof files that start with a byte-order mark keep it. A community contribution.

    rig proof add --file keeps a leading UTF-8 byte-order mark in the artifact instead of removing it.

    #270 · thanks @BortlesboatLink

Context & skills 1

  • ChangedSkill setup commands now exit with an error when a skill you selected is skipped for uncommitted changes. They only inspect unless you ask them to apply, and applying still sets up the other skills.

    rig context work-install --runtime <runtime> and rig skill loadout --runtime <runtime> exit 1 when a selected skill is skipped for uncommitted catalog content. They only inspect by default; applying with --apply-skills or --apply still reconciles the remaining clean skills.

    Exit 1 alone doesn't tell you whether files were changed.

    #1031Link

Setup & platform 4

  • ChangedAfter upgrading the CLI, restart the daemon so it actually runs the new version. Nothing in the database changes this time.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. The running daemon keeps its old build until it restarts. This release has no database migrations, and the bundled openrig-core plugin stays at version 0.1.8.

    Link

  • ChangedBuilding OpenRig from source no longer needs Unix shell tools for its final step. No dependencies or install scripts changed. A community contribution.

    Building from source: the CLI and TUI build scripts now finish their output with one Node script, scripts/prepare-workspace-build.mjs, instead of chmod, mkdir and cp, so they no longer need POSIX shell tools. No npm dependencies or install scripts changed.

    This hasn't been run on Windows yet. WSL2 is still the way to run OpenRig there.

    #1033 · thanks @dajiaohuangLink

  • ChangedThe architecture and CLI reference docs are up to date for 0.6.7.

    The architecture and CLI reference docs were brought up to date for 0.6.7.

    #1015Link

  • ChangedThe README, guides and architecture docs are up to date for 0.6.8.

    The README, reference guides and architecture docs were brought up to date for 0.6.8, and the what-changed note, capability map and changelog written for it.

    #1041, #1039Link

OpenRig 0.6.7Ask the coding agent you already use to set OpenRig up for you.17 added42 changed40 fixed

11 contributors · Release notes

Highlights

  • ChangedYour coding agent's rigs skill now covers the whole way from install to the operator: when the install is done, how to pass the operator your goal, folder and branch, and how to bring the operator's questions back to you.

    The rigs skill carries the whole route from install to the operator: when the install is finished, how to hand the operator your goal, folder and branch, how to relay the operator's questions to you, and what to give you when no window can open.

    #909, #964, #971, #982, #988Link

  • AddedWhen your agent finishes installing or starting OpenRig, it now opens the dashboard and the kernel's operator for you instead of waiting to be asked, and the same command brings them back later. It was checked on a test Mac; the full first install from nothing and Linux desktops weren't tested.

    After your agent installs or starts OpenRig, it now opens the OpenRig TUI and the kernel's operator for you as the next step, with rig terminal open saved:kernel --window, instead of waiting for you to ask. The same command brings your agents back later.

    Checked on a test Mac, where the view opened without being asked within 15 seconds of the handoff after install. The full first install from nothing, Linux desktop windows, opening the view from Claude Desktop and the plain-tmux layout without herdr weren't tested.

    #998Link

  • FixedA message or watchdog reminder can no longer answer a question that's waiting for you. Before, its Enter could pick the first option of a Claude agent's menu; now it's refused and escalated. It relies on the latest recorded hook, so hooks recorded out of order can still get this wrong.

    A message or watchdog reminder no longer answers a question for you. When a Claude agent is waiting at a question menu or an approval that OpenRig can't read on screen, a rig send message or a watchdog's reminder is refused if the agent's latest hook said it was waiting for you, and it goes up the usual escalation path instead. Before, the message's Enter could pick the first option.

    The check trusts the latest recorded hook. If an agent's hooks are recorded out of order, a message can be refused for a question that's already answered, or let through to one that's waiting.

    #1001Link

  • AddedAfter an upgrade, your agents can read what changed and what to do about it, and the upgrade skill finishes by telling you what affects you.

    An agent on an upgraded install can read what behaves differently, and what to do, with rig context get reference/whats-new.md (or $OPENRIG_HOME/reference/whats-new.md with no daemon running). The openrig-upgrade skill ends by reading it and telling you what affects you.

    #934, #1010Link

  • Changedrig doctor now tells you whether Claude Code and Codex are installed and signed in, the same way setup does. A pass means a credential is on your machine, not that the provider accepts it, and it fails for a harness you don't use.

    rig doctor checks the Claude Code and Codex installs, and a login or configured provider credential for each, the way rig setup does. It exits 1 when either is missing or has neither, including a harness you don't use, and its output and --json gain claude_install, claude_auth, codex_install and codex_auth rows.

    A pass means a login or configured provider credential is available locally, not that a provider accepts the credential or that an agent can work. It fails for a harness you don't use; only the harnesses your teams use need a login.

    #924 · reported by @readybuilderoneLink

Also in this release 94

Seats & restore 9

  • ChangedThe advisor setting now points at an agent every install has, the kernel's advisor, and writing a restore packet without flags targets the agent's own rig.

    agents.advisor_session now defaults to the kernel's advisor agent, which every install has, and rig restore-packet write without flags targets the calling agent's own rig.

    #937Link

  • ChangedBefore compacting, the daemon moves the agent's finished restore map into place itself, so the agent no longer has to run a rename that could stop at a permission prompt.

    The daemon itself moves a finished restore map into place before compacting, so the agent no longer needs a shell rename that could stop at a permission prompt.

    #965Link

  • ChangedIf a running agent's terminal fails its identity check, OpenRig says it needs attention and rig restore-check tells you what to do. A restore can still report a problem with an agent that works.

    A running agent whose current pane fails its identity check reads attention_required. The stored startup result moves to storedStartupStatus, and rig restore-check names the verdict and what to do.

    A restore can still report a problem with an agent that works (#273), as in 0.6.6.

    #940Link

  • FixedAfter a daemon restart, an agent waiting for your approval still shows as needing attention, so it isn't missed.

    After a daemon restart, an agent waiting at an approval keeps showing as needing attention.

    #885Link

  • FixedYou can hand the same role over to a fresh agent as often as you need, and running a handover again recovers one that stopped halfway.

    rig seat handover <seat> works on the same agent again and again, and running it again recovers an agent left half handed over.

    #987 · reported by @Kero-66Link

  • FixedAn agent taking over from a Codex agent now sees its predecessor's messages in the recap. A community contribution.

    An agent taking over from a Codex predecessor now sees its messages in the recap.

    #848 · thanks @rudycelekliLink

  • FixedAfter Claude compacts a long-running agent's context, the agent still gets its refocus context instead of losing it to a prompt, and repeated failures raise one issue you can find. Checked on a fresh test install, not yet on a long-running one.

    After a managed Claude compaction, the agent's refocus context arrives with the restore request instead of being lost to the acknowledgement prompt, also when the request arrives wrapped as pasted text. If refocus fails three times in a row for an agent, one issue appears on the stream (rig stream list --tag refocus). A per-agent refocus health file is kept under $OPENRIG_HOME/refocus/.

    Checked on a fresh test install; it hasn't been proven on a long-running install.

    #928, #972, #975Link

  • FixedA team you started fresh and then shut down cleanly comes back with rig up, instead of being refused for lack of a snapshot. A community contribution.

    rig up restores an agent that was launched fresh and then stopped with a clean rig down, instead of refusing with no_snapshot.

    #955 · thanks @oodadoudou · reported by @AdamWhitehurstLink

  • FixedA very long snapshot history no longer breaks the cleanup of old snapshots. A community contribution.

    A very long snapshot history no longer breaks retention.

    #836 · thanks @rudycelekliLink

Queue & messaging 14

  • AddedAgents can find the built-in starter and factory teams by topic from the start, because their leads publish who's on the team at first start.

    The built-in starter and factory leads publish their team's roster at first start, so rig roster find <topic> knows those teams.

    #918Link

  • ChangedA periodic reminder now waits one full interval before it first fires, instead of firing as soon as you set it up. A community contribution.

    A periodic reminder first fires one interval after you register it, not immediately.

    #860 · thanks @lab1207 · reported by @d3fvxlLink

  • ChangedPicking up a blocked task clears what it was blocked on, and marking it blocked again without saying on what reuses the previous blocker. A community contribution.

    Claiming a blocked task clears its blocker, and rig queue update <id> --state blocked without --blocked-on blocks it again on the previous one.

    #761 · thanks @rudycelekliLink

  • ChangedWhen a workflow step is sent back and redone, every step that depends on it runs again, even ones that had already passed. A community contribution.

    When a workflow step that was sent back completes again, the steps that depend on it run again, including ones that had passed.

    #817 · thanks @awss1i · reported by @AdamWhitehurstLink

  • ChangedWorkflow commands use the workflow file in the folder you're in. A community contribution.

    rig workflow validate, instantiate and run use the file in your current folder.

    #845 · thanks @rudycelekliLink

  • ChangedWaiting on a chatroom with a timeout now stops at the deadline with exit code 1, instead of printing a message that arrived too late. A community contribution.

    rig chatroom wait --timeout exits 1 at its deadline instead of printing a late message.

    #968 · thanks @rudycelekliLink

  • ChangedMessages from rig gateway human now say that OpenRig supports one configured human.

    rig gateway human messages say OpenRig supports one configured human.

    #961Link

  • FixedA waiting task's timer shows when it will really go off, never as a date in 1970.

    A waiting task's timer shows when it will really fire, never as a 1970 date.

    #946 · reported by @d3fvxlLink

  • FixedA timer length OpenRig can't read, such as 7d, now gets an error instead of silently doing nothing. Use hours, such as 168h. A community contribution.

    An invalid --wake-after, such as 7d, prints an error instead of exiting silently; use hours, such as 168h.

    #945 · thanks @bpamiriLink

  • FixedResuming a workflow at a failure ID that doesn't match is refused, instead of rerunning a different failure. A community contribution.

    rig workflow resume --occurrence with an ID that matches no unresolved failure is refused instead of rerunning a different one.

    #757 · thanks @rudycelekliLink

  • FixedRunning or watching a workflow that was aborted now exits with code 3 instead of waiting forever. A community contribution.

    rig workflow run and watch exit 3 for an aborted run instead of waiting forever.

    #847 · thanks @rudycelekliLink

  • FixedAsking for chatroom history since a time it can't read now fails, instead of telling you there are no messages. A community contribution.

    rig chatroom history --since with a value it can't read fails instead of printing "No messages.", and the error shows control characters as text.

    #930, #991 · thanks @DeryFerdLink

  • FixedWatching a chatroom no longer jumbles messages at the switch from history to live. A community contribution.

    rig chatroom watch keeps messages in order while switching from history to live.

    #760 · thanks @rudycelekliLink

  • FixedWatchdog history keeps the right entries when several share a timestamp. A community contribution.

    Watchdog history keeps the right entries at tied timestamps.

    #753 · thanks @rudycelekliLink

Claude 5

  • ChangedA Claude agent's activity hook now lives in OpenRig's own state folder instead of a script inside your project. It moves at each agent's next launch.

    At a Claude agent's next launch, its activity hook points at $OPENRIG_HOME/state/claude-activity-hooks/ instead of a script inside the project.

    #870 · reported by @puniservLink

  • ChangedClaude Code agents in your teams can read help for the commands that start and stop teams without a permission prompt, and allowed commands match however they're written. Starting or stopping a team still asks. Only one help command was checked live, and Codex team agents don't ask before these commands yet.

    In Claude Code team agents, help on lifecycle commands, such as rig down --help and rig bundle install -h, runs without a prompt, and common spellings of allowed commands match too: quoted or absolute paths, env, command and exec, and a project's vitest and jest. Real lifecycle actions still ask. It works through a command hook in the agents' launch settings, and no settings file is written.

    Checked in a live Claude session for only one selected lifecycle-help command; source and parser coverage is broader. Codex team agents don't yet ask before lifecycle commands such as rig up and rig down; Claude Code team agents do.

    #927 · reported by @jajabongLink

  • FixedThe status-line command OpenRig writes for a Claude agent now quotes its paths. It's rewritten at each agent's next launch. A community contribution.

    At a Claude agent's next launch, OpenRig writes its status-line command in .claude/settings.local.json with quoted paths.

    #852 · thanks @rudycelekliLink

  • FixedA running Claude agent launched with inline permission settings is no longer mistaken for one that needs attention. This fixes a known issue from 0.6.6.

    OpenRig reads a Claude agent's session from its process correctly when permission settings are passed inline, so a running agent isn't misread as needing attention. This fixes 0.6.6's known issue #921.

    #933 · reported by @HSJ-BanFanLink

  • FixedWhen OpenRig types a command to resume a Claude conversation, it quotes the resume token, so the shell can't misread it.

    The resume token is quoted when OpenRig types a resume command.

    #798Link

Codex 4

  • AddedIf a Codex agent needs a newer Codex, the operator explains it and offers to update it. The starter's Codex reviewer still needs a Codex newer than 0.145.

    The operator explains a Codex agent that needs a newer Codex and offers to update it.

    The starter's Codex reviewer still needs a Codex newer than 0.145, as in 0.6.6.

    #916Link

  • ChangedCodex agents in your teams no longer stop at launch to offer a Codex update. Updating Codex is up to you or the operator.

    Managed Codex launches pass -c check_for_update_on_startup=false, so a Codex agent doesn't stop at Codex's update offer.

    Updating Codex is left to you or the operator.

    #986Link

  • FixedIf Codex shows a sign-in or version notice at the very end of a restore, the agent is flagged for attention with the last lines of its screen, and a late "no saved session" starts fresh. A community contribution.

    A sign-in or incompatible-client notice that appears at the last moment of a Codex restore is reported as needing attention with the screen's last lines, and a late "no saved session" retries fresh.

    #759 · thanks @rudycelekliLink

  • FixedOpenRig finds the conversation of a Codex agent whose home folder path contains spaces. A community contribution.

    OpenRig finds a Codex agent's conversation when its home path contains spaces.

    #851 · thanks @rudycelekliLink

Pi 2

  • AddedPi agents tell you at start whether they have a sign-in or provider key, and how to add one, and launch checks compare your Pi version with the tested one. Pi agents weren't tested beyond automated tests.

    Launch preflight reports the Pi version against the tested baseline, and a Pi agent says at start whether it has a stored sign-in or provider key, and how to provide one.

    Pi agents weren't tested beyond automated tests.

    #938Link

  • AddedPi agents using MiniMax models can get their API key passed through once you allow it. A community contribution. Pi agents weren't tested beyond automated tests.

    Pi agents on minimax/<id> models can receive MINIMAX_API_KEY when it's in recovery.provider_auth_env_allowlist.

    Pi agents weren't tested beyond automated tests.

    #891 · thanks @bobbiejaxnLink

Slack 5

  • AddedEach team, or a single agent, can post to its own Slack channel, and rig slack verify checks the app is in each one. Replies are matched by timestamp alone, private channels aren't supported, and live Slack wasn't tested.

    rig slack channel-map set <rig-or-seat> <channel>, list and remove send a rig's or an agent's posts to its own Slack channel. An agent's entry wins over its rig's, and anything unmapped uses the default channel. rig slack verify checks the app is in every mapped channel, and the TUI shows the map.

    Replies are matched to a thread by its timestamp alone, so two mapped threads with the same timestamp in different channels could route a reply to the wrong agent. Missed-message recovery covers the default channel only, and private channels and direct messages aren't supported targets. Live Slack wasn't tested.

    #944 · thanks @bpamiri · reported by @mlc-factory-botLink

  • AddedReact to an agent's Slack question with an emoji and the agent gets a task saying who reacted and how. It doesn't answer the question, your Slack app needs a new scope and event and a reinstall, and live Slack wasn't tested.

    An emoji reaction on any message OpenRig posted for an agent's question in Slack now reaches the agent that asked, as a task saying who reacted and with what.

    It doesn't answer or close the question. An existing Slack app needs the reactions:read scope and the reaction_added event added, then a reinstall; rig slack verify warns while the scope is missing but doesn't check the event. A reaction on a reply in the question's thread, rather than on OpenRig's own messages, is ignored. Live Slack wasn't tested.

    #931, #947 · reported by @floynk-agentLink

  • ChangedAn agent's long question in Slack arrives as numbered replies in its thread, and if it still can't be posted, the agent is told instead of you never seeing it. Live Slack wasn't tested.

    A question too long for one Slack message is posted as numbered replies in its thread. If it still can't be posted, the agent gets a task saying so, instead of the question silently not arriving.

    Live Slack wasn't tested.

    #929 · reported by @floynk-agentLink

  • FixedIf you reply in a Slack thread and also send the reply to the channel, the agent that asked still gets it. A community contribution.

    A Slack reply sent with "Also send to #channel" ticked now reaches the agent that asked.

    #910 · thanks @Coder8124 · reported by @floynk-agentLink

  • FixedWhen Slack's connection stalls while reconnecting, the daemon keeps trying instead of going quiet. A community contribution.

    If Slack's connection stalls while reconnecting, the daemon retries instead of going quiet.

    #942 · thanks @tianqizhao0704 · reported by @z4ccLink

TUI 11

  • AddedYour agents open wherever your own agent is running: a herdr space, a new Terminal window or a Ghostty tab, or a new window from Claude Desktop, iTerm or VS Code on a Mac. Opening from Claude Desktop isn't proven on a real machine yet.

    The view opens where your agent runs. Inside herdr it opens as a focused openrig kernel space, in Terminal as a new window that copies the size of your front window when it can, and in Ghostty as a new tab. From Claude Desktop, iTerm or VS Code on a Mac it opens a new Ghostty (1.3 or newer) or Terminal window at that app's default size, and macOS may ask you to allow that.

    Opening the view from Claude Desktop hasn't been proven on a real machine.

    #970, #998Link

  • AddedOn a Linux desktop the view opens in GNOME Terminal, Konsole or xterm at a readable size. Linux desktop windows weren't tested.

    On a Linux desktop, the view opens in GNOME Terminal, Konsole or xterm and asks for a readable size.

    Linux desktop windows weren't tested.

    #952, #970Link

  • AddedWhile you choose a first team, the operator shows you each team's graph in the shared TUI.

    While presenting the first-team choices, the operator shows each team's graph in the shared TUI.

    #948Link

  • Changedrig terminal open now opens a new desktop window by default. If you'd rather add your agents as tiles in a herdr or cmux workspace you already have open, name it with --provider.

    rig terminal open <view> opens a desktop window by default. To add tiles to a herdr or cmux workspace that's already open, pass --provider herdr or --provider cmux.

    #954Link

  • ChangedYour own herdr config is used as it is. OpenRig writes a private herdr config file of its own only when you don't have one.

    If you have your own herdr config, OpenRig uses it unchanged. Only when you have none does it write a private .openrig-herdr-<hash>.toml in herdr's config folder.

    #969, #998Link

  • ChangedThe kernel view fits your terminal: in a narrow one the operator gets the whole first tab, in a wide one the dashboard and the operator share it. A kernel view you saved yourself still wins.

    The default saved:kernel view's layout follows your terminal's width. Under 120 columns the operator fills the first tab; from 120 columns the dashboard and the operator share it; the advisor always has its own tab. A kernel view you saved yourself still wins.

    #978, #998Link

  • ChangedOver SSH, in CI or anywhere without a display, you're told why no window opened and given the exact command to run instead.

    When no window can open, over SSH, in CI or with no display, rig terminal open says why and prints the exact command to run instead.

    #954, #970Link

  • ChangedThe TUI's Open terminals action works the same way and doesn't need herdr. When no window can open, it shows you the command to reach each agent.

    In the TUI, the Open terminals action uses the same launcher, works without herdr, and shows the attach command for each agent when no window can open.

    #959Link

  • FixedOpening the same herdr view again takes you back to the workspace that's already open, and your existing windows are never resized.

    Opening the same herdr view again reuses the open workspace, and your existing windows are never resized.

    #957, #958Link

  • FixedOpening a large view gets up to 45 seconds to finish, instead of reporting a timeout after 5. A community contribution.

    rig terminal open waits up to 45 seconds for a larger view to finish opening instead of reporting a timeout at 5.

    #758 · thanks @rudycelekliLink

  • FixedIn the TUI, a rig, host, pod or agent address now works from any page.

    In the TUI, a rig, host, pod or agent address works from any page.

    #984Link

CLI & hosts 12

  • AddedA mission can be checked against a ref other than main, and a ref that can't be resolved reads as INDETERMINATE rather than guessing. A community contribution.

    A mission can declare arrangement.source.integration_ref in mission.yaml, so rig view execution checks its work against that ref instead of main. A ref that's invalid or can't be resolved reads INDETERMINATE.

    #682 · thanks @opencode13241-eng · reported by @aanestesiaLink

  • ChangedScripts that tear down a rig on another host can tell when it went wrong: rig down --host exits 2 when the remote teardown reports errors. A community contribution.

    rig down --host exits 2 when the remote teardown reports errors.

    #756 · thanks @rudycelekliLink

  • ChangedBefore stopping a team, rig down shows one line per agent with what it was last doing, so you can see what you're interrupting.

    Human-mode rig down prints one line with each agent's last known activity before stopping.

    #922Link

  • ChangedHelp examples and guides no longer mention teams that were retired.

    Help examples and reference guides no longer use retired team names.

    #935Link

  • FixedNames with a % in them work for agents, pods and agent images. A community contribution.

    Agent, node, pod and agent-image names containing % are looked up correctly.

    #844 · thanks @rudycelekliLink

  • FixedOpenRig handles tmux session names with | or leading and trailing spaces, and reads each agent's launch settings from its own session only. A community contribution.

    Discovery and capture keep tmux session names containing | or edge spaces, and OpenRig reads an agent's launch settings from exactly its own tmux session.

    #752, #755 · thanks @rudycelekliLink

  • Fixedrig usage top keeps agents that reused a name apart. A community contribution.

    rig usage top no longer mixes up agents that reused a name.

    #835 · thanks @rudycelekli · reported by @d3fvxlLink

  • FixedUsage series filtered by start and end times compare the actual times, not the text of the timestamps. A community contribution.

    rig usage series --since/--until compare times as moments, not text.

    #840 · thanks @rudycelekliLink

  • FixedReading a transcript's tail or searching it while it's being updated gives you a consistent copy. A community contribution.

    rig transcript --tail and --grep read a consistent copy while the file is being replaced.

    #843 · thanks @rudycelekliLink

  • FixedMoving, shipping or closing a piece of work with rig scope copes with unusual folder paths, and a failed attempt leaves the mission unchanged. A community contribution.

    rig scope slice move, ship and close work when the workspace path starts with -, don't change a mission's membership when they fail, and check the folder they work on by its literal path.

    #974, #976, #1003 · thanks @rudycelekliLink

  • FixedCreating a mission or a piece of work copies your text exactly, and updating its details keeps your keys, comments and quoting. A community contribution.

    rig scope mission create and slice create copy your text exactly, and frontmatter updates keep keys, comments and quoting as written.

    #977, #979 · thanks @rudycelekliLink

  • FixedNaming a piece of work for a mission finds the right one, even when an unrelated folder has the same name. A community contribution.

    A bare name with --mission resolves to the right piece of work past an unrelated folder of the same name.

    #1004 · thanks @rudycelekliLink

Specs & bundles 8

  • ChangedA bundle you create, or install from a GitHub link, is named after the rig it contains instead of a generic name. --name still overrides it.

    rig bundle create, and rig up <GitHub link>, name a bundle after the name in its rig.yaml instead of my-bundle or github-bundle. --name still wins.

    #985Link

  • ChangedPackage commands resolve relative paths from the folder you run them in, not from the daemon's folder. A community contribution.

    rig package validate, plan and install resolve relative paths, and the default --target ., from the folder you run them in, not the daemon's.

    #754 · thanks @rudycelekliLink

  • ChangedWhen rig bundle check finds a problem, it tells you which file it's in.

    rig bundle check names the file in each finding.

    #985Link

  • ChangedTo submit a team, the docs now point you to the openrig-registry repository.

    The docs name openrig-registry as the place to submit a team.

    #951Link

  • ChangedReinstalling a stopped team replaces conflicting files only in the folder it was installed into, after backing them up. Install into any other folder and conflicting files are refused before anything is written. Teams installed before 0.6.7 get a recorded folder at their next install.

    Reinstalling over a stopped team backs up and replaces conflicting files only in the folder the team was installed into. Installing into another folder gets first-install behaviour, refusing conflicting files before anything is written.

    Teams installed before 0.6.7 have no recorded folder until their next bundle install.

    #901Link

  • ChangedIf you script against the daemon, a bundle install refused for a conflicting file returns HTTP 400 with a code, and other known refusals return 409 with theirs.

    A bundle install refused for a conflicting file returns HTTP 400 with a code, and other known refusals carry theirs with 409.

    #926Link

  • ChangedA rig spec with malformed pods, members or edges gets ordinary validation errors you can act on. A community contribution.

    rig spec validate reports malformed pods, members and edges as ordinary errors.

    #846 · thanks @rudycelekliLink

  • FixedForcing a bundle install past its version check no longer skips the bundle's safety check. A community contribution.

    rig bundle install --skip-version-check --force still runs the bundle's safety check.

    #876 · thanks @DeryFerdLink

Context & skills 10

  • AddedYour own Claude Code and Codex sessions get two OpenRig skills, kept current on every upgrade, including rigs, which walks an agent from installing OpenRig to a team doing the work. A rigs copy you added yourself with npx is left alone; remove it if you want OpenRig to keep it updated.

    The daemon now copies two skills for your own Claude Code and Codex sessions into ~/.claude/skills and ~/.agents/skills: rigs, which takes an agent from installing OpenRig to a team doing the work, and refocusing. They're refreshed on every upgrade.

    A rigs copy you added earlier with npx skills add has no OpenRig marker, so it's left alone and not refreshed; remove it if you want OpenRig to keep it current.

    #967, #928Link

  • ChangedThe capability map your agents read to learn what OpenRig can do is up to date for 0.6.6 and 0.6.7.

    The capability map agents read to learn what OpenRig can do is refreshed for 0.6.6 and 0.6.7.

    #905, #1010Link

  • ChangedBefore a handover or compaction, agents are taught to write their recap with one command, so whoever picks up the work starts from it.

    The handover and compaction skills teach agents to write their recap with rig context recap-write before a handover or compaction.

    #1002 · reported by @csaxton171Link

  • ChangedAdding a context pack from Git fetches only the current commit by default, and falls back to a full clone, with a warning, if the server won't allow that.

    rig context add --git retrieves only the current commit by default, falling back to a full clone with a warning when the server refuses.

    #951Link

  • Fixedrig skill audit passes on a clean install, and its JSON output gains new fields.

    rig skill audit passes on a clean install, with new --json fields.

    #807 · reported by @d3fvxlLink

  • FixedReading one section of a context file by its address works with inline code and empty headings. A community contribution.

    In rig context get <pack>/<file>#section, an inline triple-backtick span no longer hides later headings, and an empty heading ends the section above it.

    #962 · thanks @rudycelekliLink

  • FixedThe Codex plugin files OpenRig generates in your repository are now covered by its block in .git/info/exclude, so Git ignores them.

    Files OpenRig generates under .codex/plugins/shared:openrig-core/ are added to its marked block in the repository's .git/info/exclude.

    #919 · reported by @jajabongLink

  • FixedGuidance text with $$ in it keeps its exact wording when OpenRig updates its managed sections.

    Guidance text containing $$ or similar stays as written when OpenRig rewrites its managed blocks.

    #908 · reported by @adampogLink

  • FixedIf a plugin skill's source can't be used any more, the agent launches with its existing copy and a warning instead of failing.

    A plugin skill copy whose remembered source can no longer be projected is kept, with a plugin_skill_kept warning, instead of failing the launch; an agent selecting that plugin refreshes it at its next launch.

    #819Link

  • FixedA project declared at the root folder no longer ties with a more specific project when OpenRig works out which project your folder belongs to.

    A project declared at / no longer ties with a deeper project when OpenRig picks one from your working folder.

    #857Link

Setup & platform 14

  • AddedInstall OpenRig with one command, or preview it first: the dry run prints the four steps and changes nothing. If only provider sign-ins are left at the end, the install itself worked. The full first install from nothing wasn't tested.

    The README, the getting-started guide and the help guide show a one-command install with a stable link, and a --dry-run preview that prints its four steps and changes nothing. If only provider sign-ins are left, the install itself finished. The script is the repository's scripts/install.sh, which isn't in the npm package; its closing and plan text changed too.

    The full first install from nothing wasn't tested.

    #917, #916, #950Link

  • AddedIf permission prompts are slowing you down, the operator points you to the workshop team and tells you plainly what access it takes.

    If permission prompts are slowing you down, the operator and the guides point to the workshop team and say plainly what access it takes.

    #939Link

  • AddedIf kernel agents fail at first start because your tmux build crashes, the getting-started guide shows how to check for it and recover.

    The getting-started guide covers kernel agents that fail at first start on a tmux build that crashes, with a check and a recovery.

    #999 · reported by @MichelMabinuolaLink

  • AddedTo run OpenRig on Windows, use WSL2: the getting-started guide records one user's working setup and both ways a Pi agent can get credentials. Windows and WSL2 aren't in automated tests.

    WSL2 is the way to run OpenRig on Windows: the getting-started guide records one user's working setup and both ways a Pi agent can get credentials.

    Windows and WSL2 weren't tested in automated tests.

    #960, #963 · reported by @dajiaohuang, @jmrichardsonLink

  • ChangedAfter upgrading the CLI, restart the daemon so it actually runs the new version. On that first start it updates its database and installs the updated openrig-core plugin, which your agents pick up the next time they launch.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. The running daemon keeps its old build until it restarts. On its first start it runs two database migrations, one recording each team's install folder and one mapping replies in a Slack thread back to the question an agent asked there, and installs the updated bundled openrig-core plugin, which running agents pick up when they next launch.

    #901, #947, #928, #965, #972, #975Link

  • Changedrig setup now installs herdr for the view of your agents, by running herdr's own installer. Pass --no-herdr if you don't want a third-party installer run; if it fails, setup warns and you get plain tmux.

    rig setup installs herdr by default on macOS and Linux, for the view of your agents, by running herdr's own installer (curl -fsSL https://herdr.dev/install.sh | sh) into $HERDR_INSTALL_DIR or ~/.local/bin. Pass --no-herdr to decline it. If the install fails, setup warns and the view uses plain tmux.

    This runs a third-party installer by default. The plain-tmux layout without herdr hasn't been proven on a real machine.

    #936Link

  • ChangedOn a Mac, setup offers Ghostty once and installs it only if you ask with --ghostty. Setup no longer installs cmux, and a cmux you already have keeps working. Scripts reading setup's JSON should look for the new herdr and Ghostty steps.

    On a Mac, rig setup offers Ghostty once and installs it with Homebrew (brew install --cask ghostty) only when you pass --ghostty; --no-ghostty declines. Setup no longer installs or configures cmux, and an existing cmux keeps working. In rig setup --json, the cmux_install step is gone and herdr_install and ghostty_install appear.

    #936Link

  • ChangedAsk the CLI, setup or onboarding how to see your agents or the welcome screen, and you're pointed to the one command that opens them.

    CLI help, setup's next steps and onboarding point "show me my agents" and "the welcome screen" to rig terminal open saved:kernel --window.

    #950Link

  • ChangedIf your agent's own permission rules block a step while it installs OpenRig, the guides tell it to show you the refusal instead of reporting the install as failed.

    If the agent installing OpenRig has a tool call refused by its own permission rules, the guides tell it to show you the refusal rather than report a failure.

    #950Link

  • ChangedThe kernel's operator can look around with routine commands, read the /rigs pages and run its first-boot checks without stopping for your approval each time. In a live test it still hit one prompt in nine calls.

    The kernel's operator runs routine inspection (cd, pwd, echo, wc, sort, python, command -v and WebFetch) without asking, reads /rigs pages with WebFetch, and runs its first-boot checks as separate commands. The kernel's Claude agents get the launch-settings command hook too, with a wider allowance, and no settings file is written.

    In a live Claude session the operator still hit one prompt in nine calls.

    #983, #994, #932 · reported by @jajabongLink

  • ChangedSetup's permission question now recommends the same default your teams use, and offers extra remembered allowances only if you want them.

    Setup's permission question now matches the team default: it recommends keeping it and offers extra remembered allowances only if you want them.

    #916Link

  • ChangedTo stop everything, the operator and the getting-started guide give you the order: each rig, the kernel last, then the daemon.

    For "stop everything", the operator and the getting-started guide give the order: each rig with rig down, kernel last, then you run rig daemon stop.

    #932 · reported by @jajabongLink

  • ChangedThe README, reference guides, architecture docs and changelog were brought up to date for 0.6.6 and then 0.6.7.

    The reference guides were brought to the 0.6.6 release, the architecture docs restamped to it and CHANGELOG.md gained its 0.6.6 section; the README and reference guides were then brought to 0.6.7.

    #903, #902, #906, #1009Link

  • FixedIf you use the web UI, a terminal view that fails to attach closes that viewer and leaves the daemon running.

    With the web UI on, a terminal view that fails to attach closes that viewer instead of stopping the daemon.

    #907 · reported by @oSquashBlossomoLink

OpenRig 0.6.6The operator picks your team and starts it on your yes, and you can install a team straight from a GitHub link.31 added39 changed1 redesigned39 fixed

11 contributors · Release notes

Highlights

  • AddedAfter install, the first agent you meet is the kernel's operator: it asks what you want to build and recommends one of three teams. It's guidance the agent follows, not a scripted flow, and in the first-user test the person still needed help attaching terminals.

    After you install OpenRig, the kernel's operator agent greets you first and asks, once, what you want to build or change. It offers three teams, starter, workshop and factory, with one recommendation and a drawing of each.

    This is guidance the agents follow, not a scripted wizard; how closely an agent follows it is what OpenRig's first-user runs check. In the first-user test on a Linux VPS the person reached the operator and the goal reached the team's lead, but they were guided to attach a terminal five times, which counts as help. The final package wasn't put through another journey.

    #858, #862Link

  • AddedBefore you install a team, you can see what it will do on your machine: its models, whether permission prompts are off, the files and startup actions it brings, what it writes and which outside domains it uses. The author's setup steps are shown, never run.

    See a team before you install it. rig bundle inspect, and the view printed before rig bundle install and rig up <bundle>, show the team and models, its permission settings including whether prompts are off for every agent, files the agents receive, startup actions, writes, outside domains, the author's setup preconditions and what stays unknown until launch. Facts about one agent are labelled with that agent.

    The author's setup preconditions are shown, never run, and some facts stay unknown until launch.

    #710, #717, #723, #738, #892Link

  • AddedA team can be shared as a link to a folder on GitHub and installed straight from it, pinned to one commit and with a package digest you can check. You need git and a running local daemon.

    rig up, and rig bundle create, inspect and install, accept a public GitHub folder link (https://github.com/<owner>/<repo>/tree/<ref>/<folder>). The ref resolves to one commit, and the result reports the source, configuration ID and package digest.

    Link import needs git on your PATH and a running local daemon. It runs your git with credential helpers, hooks and global config disabled.

    #708Link

  • AddedYou don't need every provider a team was designed for: the operator adapts the team to the accounts you have, asks before launching, and passes your goal to the team's lead so you only explain it once. It's guidance the agents follow, checked by first-user runs.

    The operator fits the team you pick to the providers you have by writing an adapted copy, shows you the plan and launches only on your yes. It then shows you the team and hands your goal to the team's lead as a task, so the lead starts from that goal instead of asking again.

    Guidance for the agents, checked by first-user runs. In the first-user test the person was guided to attach a terminal five times, which counts as help.

    #862, #880Link

  • ChangedClaude Code agents in your teams can run OpenRig commands, read the project and run its tests without a permission prompt, but still ask before starting, stopping or installing teams. It's an allow list, not a sandbox, and applies only where you haven't set permissions yourself.

    Claude Code agents in your teams need fewer permission prompts. OpenRig passes an allow list and an ask list at launch, so rig commands, reads inside the project and common test commands such as npm test, pytest, go test and cargo test run without a prompt, while lifecycle commands such as rig up, rig down, rig bundle install, rig seat stop and rig daemon stop still ask.

    Applies outside the kernel at an agent's next launch, resume, fork or handover, only when no member or rig permission_policy and no saved permission choice is set; permission_policy: none keeps the old behaviour. These are command allowances, not containment: a project's test command runs project code. Your own ask and deny rules still apply, and no settings file is written. Asking before lifecycle commands works in Claude Code team agents only; Codex team agents don't ask yet. In a Claude Code team agent, rig down --help also asks; rig help down prints the same help without a prompt. rig setup's permission question still describes the behaviour before these defaults; its text is corrected in the next release.

    #893Link

Also in this release 105

Seats & restore 7

  • AddedAgents you've already set to full bypass can launch without stopping at Claude Code's and Codex's first-launch warnings, and the rig remembers that choice through restores and handovers. You can also make it the default for new rigs.

    --non-interruptive on rig up and rig bundle install lets agents whose policy is full bypass skip Claude Code's and Codex's first-launch warnings through launch flags. The choice is saved on the rig and kept for restores, forks and handovers, and rig config set launch.non_interruptive true makes it the default for new rigs.

    Only agents whose policy is full bypass skip the warnings. Existing rigs start with it off. --no-non-interruptive clears it, with the rig down first. No harness settings file is written.

    #737, #741Link

  • AddedAgents that are slow to start can be given up to ten minutes to become ready, at launch, restore and handover, instead of the default 30 seconds.

    runtime.readiness_timeout_seconds (1 to 600, default 30) gives slow agents more time to become ready at launch, restore and handover.

    #643 · thanks @Nikhi00718Link

  • ChangedThe restore map a Claude agent writes before its context is compacted now sits in the agent's own launch folder, with a .gitignore that keeps it out of your commits. Tools that ignore .gitignore, such as rsync or zip deploys, still see it.

    Managed Claude compaction now writes its restore map inside the agent's own launch folder, at .openrig/compaction/preparation/<session>/<attempt>/RESTORE-MAP.md, with a .gitignore that keeps it out of Git.

    Tools that don't read .gitignore, such as rsync, zip deploys and Docker build contexts without .dockerignore, still see the folder. The OpenRig home is used when the workspace is unknown or unwritable.

    #685Link

  • ChangedYou can change an agent's permissions from an ordinary shell, not only from inside an agent, and an incomplete request tells you exactly which part is missing.

    rig seat set-permissions takes --operator <address>, so it works from a plain shell, and reports a missing identity, mode or reason as three separate errors.

    #689Link

  • ChangedStartup text that wasn't confirmed as sent now shows as a warning in launches, imports, restore records and the TUI, so an agent that may have missed its instructions is easy to spot.

    Startup files delivered later get the same submit check, and staged or unverified startup text shows as a warning in rig bootstrap, rig import, rig seat launch, restore records and the TUI.

    #736 · reported by @pr0xc3nt4ur1Link

  • FixedIf an agent is stuck at a provider's own prompt, such as Claude's trust dialog, OpenRig flags it for your attention instead of calling it ready, so you know someone has to answer it.

    An agent stopped at a provider's own prompt, such as Claude's trust dialog, is reported as needing attention instead of ready.

    #684Link

  • FixedIf rig down can't stop an agent, that agent keeps its CLAUDE.md or AGENTS.md, so it isn't left running without its instructions.

    When rig down can't stop an agent, it leaves that agent's CLAUDE.md, CLAUDE.local.md or AGENTS.md in place instead of stripping or deleting it.

    #662 · thanks @Vaishnavi220506Link

Queue & messaging 4

  • AddedAgents can look up which specialist to bring in for a job, and why, from rosters you keep, across teams and machines. It's a lookup only and never assigns work.

    rig roster list, show and find read JSON rosters from <workspace.root>/rosters/ and show who to involve for a purpose and why, across rigs and hosts. They never assign work.

    #697Link

  • ChangedHanding work to another agent returns as soon as the task is saved, so you aren't kept waiting on delivery. When you need to know it was delivered, add --verify.

    rig queue create, handoff and handoff-and-complete return once the change is saved, and the agent is notified after that. The result no longer reports whether that notification was delivered; use --verify to wait for delivery.

    #776Link

  • FixedAnswering an agent's numbered menu from outside its terminal now sends the digit as a keypress rather than a paste, so the menu gets the choice you meant. It hasn't been tried against a live Claude Code or Codex menu yet.

    rig send --dangerously-interact now types your answer as keystrokes instead of a paste, so a numbered menu gets the digit you sent. This addresses a known issue, #519.

    It wasn't tried against a live Claude Code or Codex menu. Upgrade the CLI and the daemon together for this.

    #663 · reported by @DianaKerimLink

  • FixedMarking a task as blocked is easier to get right: the help says you must name what it's waiting on, and naming a task this daemon doesn't have suggests waiting on something outside OpenRig instead.

    rig queue block help says --on is always required, and blocking on a task this daemon doesn't have suggests an external gate instead.

    #664Link

Claude 8

  • AddedA new Claude Code agent stopped at Claude's bypass-permissions warning no longer loses its startup instructions. Accept the warning in its terminal, and one command, which rig up prints for you, delivers them into the same conversation without a relaunch.

    If a fresh Claude Code agent stops at Claude's bypass-permissions warning, it now keeps its startup context and reports attention as bypass_consent_gate. Accept the warning in that agent's terminal, then run rig seat continue <seat> to deliver the context into the same conversation without relaunching; rig up and rig bundle install print the command.

    #740, #748Link

  • AddedYou can run Claude Code agents in Claude's own auto permission mode by picking one built-in policy, and see each agent's effective mode and where it came from. The policy is a community contribution.

    A new built-in policy, builtin:auto, launches Claude Code agents with --permission-mode auto, while Codex and Pi agents launch as they normally would. rig seat status prints the effective permission mode and where it came from, and the built-in policies are described in the RigSpec reference.

    #680, #733, #713 · thanks @shravansumanthananLink

  • ChangedNew Claude agents finish setting themselves up without anyone typing to them: after their startup text, OpenRig sends one short line asking each to run its startup check.

    After delivering a Claude Code agent's startup text, OpenRig sends one short line asking it to run its startup check, so Claude agents finish getting set up on their own.

    #719, #743, #747Link

  • FixedOpenRig reads more Claude Code screens correctly: an agent with only update or limit warnings under an empty prompt counts as idle and gets its messages, and one that's visibly working isn't mistaken for idle.

    A Claude Code pane is read as idle when update, focus-events or weekly-limit warnings sit below an empty input, in every permission mode, and a pane showing live work alongside the mode bar is read as working.

    #735, #814 · reported by @AdamWhitehurstLink

  • FixedWhen a Claude Code agent asks a question with a long list of choices, OpenRig now recognises that it's waiting on an answer.

    A tall Claude Code question picker is recognised as a waiting question.

    #745 · reported by @gopinathrimcLink

  • FixedClaude agents launched through a shell wrapper named with a version number are now recognised by their executable path, so a restore problem flagged on them can be cleared. A restore can still report a problem with an agent that works.

    OpenRig can identify a Claude process running under a shell wrapper with a version number as its name, by its executable path, so restore attention on such agents can be cleared.

    On macOS the daemon may run the built-in /usr/bin/osascript for this; whether macOS shows a permission prompt for it on a Mac that has never approved one hasn't been observed. A restore can still report a problem with an agent that works (#273); several fixes target it and it isn't fully resolved.

    #724, #730Link

  • FixedClaude agents brought back with rig up --existing keep reporting their activity to OpenRig, and a restore that can't set that up again says so.

    An agent brought back with rig up --existing keeps its Claude activity hooks, and a restore that can't reapply them now says so.

    #731, #746Link

  • FixedForking a Claude agent now quotes the parent conversation's ID in the launch command, so the shell can't misread it.

    Forking a Claude agent quotes the parent session ID in the launch command.

    #773 · thanks @DeryFerdLink

Codex 2

  • ChangedCodex agents in your teams get the same relief: routine OpenRig, read and test commands ran without prompts in testing, still inside Codex's sandbox. One difference for now: they don't ask before starting or stopping teams, as Claude Code agents do.

    Codex agents in your teams need fewer permission prompts too. They keep the workspace-write sandbox and can also write OpenRig's workspace folder and the state folder of their pod (their group of agents), and ordinary rig, read and test commands ran without prompts in testing.

    Codex team agents don't ask before lifecycle commands such as rig up and rig down yet; Claude Code team agents do. Applies only when no member or rig permission_policy, saved permission choice or named Codex profile is set; permission_policy: none keeps the old behaviour. rig setup's permission question still describes the behaviour before these defaults; its text is corrected in the next release.

    #893Link

  • FixedCodex agents no longer get stuck at launch, resume or fork when Codex 0.160 shows its newer update menu.

    Codex agents no longer stall at launch, resume or fork when Codex 0.160 shows its update menu with the new header.

    #861Link

Pi 5

  • ChangedOh My Pi agents using Anthropic, OpenAI or LiteLLM models can send requests to a custom endpoint, such as a gateway, once you allow that provider's base-URL variable. If you already allow one, those agents now use it.

    An Oh My Pi agent whose model is written anthropic/…, openai/… or litellm/… now also receives that provider's base-URL variable when you allowlist it in recovery.provider_auth_env_allowlist.

    If you already allowlist ANTHROPIC_BASE_URL or OPENAI_BASE_URL, those Oh My Pi agents now send requests there. Oh My Pi agents weren't tested beyond automated tests.

    #744 · thanks @PowellTravisLink

  • FixedA rig with a Pi agent no longer fails its pre-launch check just because the daemon can't see pi on its PATH, since the agent's own shell finds it at launch. Pi flag errors also name your Pi version.

    A rig with a Pi agent no longer fails preflight when pi isn't on the daemon's PATH; it warns, and the pane's shell finds Pi at launch. Pi flag errors name the Pi version.

    Pi agents weren't tested beyond automated tests.

    #655Link

  • FixedPi agents keep talking to the right daemon as the right agent, even when your shell startup files set conflicting values.

    Pi agents keep their daemon routing and identity when shell startup files set conflicting values.

    Pi agents weren't tested beyond automated tests.

    #666Link

  • FixedWhen a Pi agent can't find an API key, the error now tells you what to set.

    A Pi agent failing with "No API key found" now says what to set.

    Pi agents weren't tested beyond automated tests.

    #667Link

  • FixedWhen Oh My Pi quits during startup, you see how it exited and its last error output, so you can tell why.

    When Oh My Pi exits during startup, the error says how it exited and shows its last stderr lines.

    Oh My Pi agents weren't tested beyond automated tests.

    #646 · thanks @1solomonwakhunguLink

Slack 2

  • AddedIf the daemon loses its Slack connection for a while, top-level channel messages posted during the gap still reach your agents, late and marked as recovered, instead of being missed. rig slack status shows the connection and whether it's catching up.

    Top-level Slack messages posted while the daemon was disconnected now arrive late, as tasks marked "Recovered after a gap". rig slack status shows the live connection and recovery state.

    Needs Slack inbound configured. Each channel gets a recovery checkpoint on the first daemon start, and history before that checkpoint stays unknown. Live Slack recovery wasn't tested.

    #742Link

  • FixedOpenRig's saved Slack connection state stays intact if the daemon crashes while writing it.

    Slack gateway state survives a crash in the middle of a write.

    #669 · thanks @rudycelekliLink

TUI 7

  • AddedOne command opens the kernel's TUI, advisor and operator side by side on any kernel, Claude-only, Codex-only or mixed, with nothing to set up first. A kernel view you saved yourself still takes priority.

    rig terminal open saved:kernel works without any saved-view file: it opens the TUI, the advisor and the operator side by side, for Claude-only, Codex-only and mixed kernels. A view you saved yourself under the name kernel still wins.

    #830, #854Link

  • AddedWithout herdr or cmux, you still get the exact tmux or ssh command to reach each agent, and the shared TUI is labelled as the dashboard, not the place to talk to agents.

    Without herdr or cmux, setup, the TUI preview and a failed rig terminal open give an exact tmux or ssh -t attach command for each agent, and rig tui --shared is named as the dashboard, not the conversation.

    #831, #833, #878Link

  • AddedOpen a team's spec in the TUI to see how its agents fit together as a graph, then launch it from there: it asks for a working folder and runs the real rig up.

    A rig spec opened in the TUI starts on a graph of its topology, with Launch: it asks for a working folder and hands the terminal to the real rig up.

    #867, #874Link

  • ChangedWhen a team starts, you know where to go: watch it from the dashboard, and talk about the work in the lead's pane.

    Team views say the dashboard is the overview and the lead's pane is where you talk about the work.

    Shaped by an earlier first-user run on macOS, which wasn't rerun on the final package.

    #884, #890Link

  • ChangedOpen the TUI and you're at your work right away, even before any team is running, rather than on a start page. The Start page is one key away, on S.

    The TUI goes straight to the work views once it has read the daemon, even when no rig is running. The Start page is still there on S.

    #818Link

  • FixedThe TUI's recent task activity takes less work to load when there's a long history behind it.

    The query behind the TUI's recent queue activity does less sorting on large histories.

    #816Link

  • Fixedrig terminal open now uses the daemon's own tmux, and with herdr it reports a pane that closes at once as degraded instead of treating it as working.

    rig terminal open starts tiles with the daemon's own tmux, and with herdr reports a pane that exits at once as degraded.

    #715Link

CLI & hosts 14

  • AddedTools that collect OpenRig's history can read it a page at a time through the CLI, with any gaps marked, instead of reading OpenRig's database directly.

    rig telemetry events, transitions and tenures read one bounded page of retained history at a time, with a cursor and explicit gaps, so collectors no longer read OpenRig's database.

    #696Link

  • AddedInventory timeouts are easier to diagnose: requests marked with a diagnostic header are traced in the daemon's slow-operation log.

    Requests that carry an X-OpenRig-Diagnostic-Attempt header are traced in the daemon's slow-operation log, to help diagnose inventory timeouts.

    #726Link

  • AddedThe project commands shadow-drain and shadow-stop now work from an ordinary shell, not only from inside an agent.

    rig project shadow-drain and shadow-stop take --actor, so they run from a plain shell.

    #665 · thanks @Coder8124Link

  • ChangedBefore you stop or restart a running team, the help tells you what that does to the work in progress.

    Lifecycle help says what stopping or restarting a live team does to its work.

    A text change, packaged without a new journey run.

    #895Link

  • FixedStopping services through the daemon's API removes their data volumes only when the request explicitly asks for it. The rig env down --volumes command works as before.

    Tearing down services through the daemon's API deletes volumes only when the request says volumes: true as a JSON boolean. rig env down --volumes is unchanged.

    #668 · thanks @rudycelekliLink

  • Fixedrig host pair always gives up eventually, even when given an infinite or oversized timeout.

    rig host pair --timeout caps an infinite or overflowing value at about 25 days instead of waiting forever.

    #734 · thanks @DeryFerdLink

  • FixedWhen rig whoami can't find the agent, the error names the daemon it reached, so you can tell if it's talking to the wrong install.

    When rig whoami or rig health --self can't find the agent, the error names the daemon it reached.

    #660Link

  • FixedPointing rig project experimental at a named pipe now gets a clear refusal instead of a hang.

    rig project experimental refuses a FIFO instead of hanging.

    #670 · thanks @rudycelekliLink

  • Fixedrig capture now shows an empty agent screen as empty.

    rig capture shows an empty pane as empty.

    #671 · thanks @rudycelekliLink

  • FixedOpenRig's MCP server exits when its input closes, and keeps using the daemon address it found, including IPv6 ones.

    rig mcp serve shuts down when its input ends, and keeps the daemon address it found, including IPv6.

    #674, #676 · thanks @rudycelekliLink

  • FixedMission titles with colons, hash signs or quotes no longer break the mission's file.

    A mission title with : , # or quotes writes valid frontmatter.

    #768 · thanks @adampogLink

  • Fixedrig env logs --tail 0 now prints no earlier lines, as you asked.

    rig env logs --tail 0 prints no past lines.

    #673 · thanks @rudycelekliLink

  • Fixedrig env status keeps working when a cached service record is damaged.

    rig env status survives a corrupt cached service record.

    #675 · thanks @rudycelekliLink

  • FixedAgent transcripts now read correctly where text was erased with several backspaces in a row.

    Transcript cleanup applies runs of backspaces correctly.

    #677 · thanks @rudycelekliLink

Specs & bundles 23

  • AddedA team can come in several ready-made configurations, such as which runtime each agent uses, and you choose one when you install it.

    A bundle can declare presets in configurations.yaml. rig bundle configurations <spec> lists them, and --preset <name> or --seat pod.member=runtime picks one.

    #704Link

  • AddedInstall a team and point all its agents at your project folder in one step, separately from where the team itself is installed.

    rig bundle install --cwd <dir> sets every agent's working folder, and --target sets the install folder.

    #692Link

  • AddedTeam authors can check a bundle against the authoring rules on their own machine before sharing it. The check is advisory.

    rig bundle check <folder> checks a bundle against the authoring rules, locally.

    It's advisory.

    #708Link

  • AddedWhen you package a team, it can carry a context pack kept outside the rig folder and the project the team works in, so whoever installs it gets both.

    rig bundle create --context-pack <dir> carries a context pack from outside the rig folder, and --project-dir <dir> carries the project the rig works in.

    #694, #700, #716 · thanks @DeryFerdLink

  • AddedInstalling a team you already have now asks what to do: use it, stop and replace it, or cancel. A running team is left alone, and conflicting files are backed up before a stopped one is replaced.

    Installing a team that already exists shows what's installed and offers to use it, stop and replace it, or cancel. A running team is refused before anything is written; a stopped one is replaced in the folder holding its installed manifest, with conflicting files backed up first.

    Reinstalling into another folder that holds a copy of the team's installed manifest treats that folder as the team's install folder, so its conflicting files are replaced. They're backed up first and the backup is named.

    #877Link

  • AddedPublishing your team on openrig.dev/rigs takes one pull request that adds a single file pointing at your repository. The guide ships with OpenRig.

    To share a team, open a pull request to openrig-world that adds one file naming its repository, folder and ref. Rig names on the site are unique, and the guide is docs/reference/publishing-a-rig-bundle.md, also at $OPENRIG_HOME/reference/.

    #750, #751, #810, #777Link

  • AddedIf you build tools around team bundles, the v1 formats are now documented, with JSON Schemas to validate against.

    The v1 bundle formats are documented in docs/reference/bundle-formats.md, with JSON Schemas.

    #702Link

  • AddedInstall the workshop from openrig.dev/rigs for a four-agent team that builds in any repository: its lead plans from your goal and routes work to a builder, a reviewer and QA, and nothing is published until you say so. Its agents run without permission prompts, and the view before install says so.

    The workshop, OpenRig's team for building software in any repository, OpenRig's own included, installs from openrig.dev/rigs, which shows its install command. It has a lead, a builder, a code reviewer and a QA agent; the lead starts from your goal, plans the work and routes it to the team, and nothing is published until you say so.

    It ships separately, in the openrig-world repository, needs OpenRig 0.6.6 and isn't built in, so rig up workshop doesn't resolve. Its agents run with permission prompts off and install non-interruptively by the team's own declaration; the view before install says so. The current workshop was checked separately with a startup check, not a full journey, and not in other configurations or with Pi. The first-user journey used an earlier workshop revision.

    Link

  • AddedA team's author can declare in its spec that it launches without first-launch warnings, and a flag you pass on the command line still overrides it.

    A rig spec can declare non_interruptive: true itself. An explicit flag still wins, and the declaration wins over the machine default.

    #892Link

  • ChangedIf you start any of these three teams by name, in scripts or by habit, switch to the new name. The old ones have no alias.

    Three specialist teams were renamed: adversarial-review is now code-review, research-team is now research and pm-team is now pm.

    There's no alias for the old names.

    #864Link

  • ChangedInstructions that say rig up first-project keep working and now start the starter team, which pairs a Claude Code builder with a Codex reviewer. On a Codex-only machine, ask the kernel's operator to adapt it, and use a Codex newer than 0.145.

    rig up first-project still works and starts starter, with a note that the team's providers changed. first-project used two Codex agents; starter has a Claude Code builder and a Codex reviewer.

    On a Codex-only machine, ask the kernel's operator to adapt it. The starter's Codex reviewer needs a Codex newer than 0.145, which refuses its model with "requires a newer version of Codex"; Codex 0.160.1 works.

    #864Link

  • ChangedSeven older built-in teams were retired. Any rig you already created from one of them keeps restoring as before.

    conveyor, demo, implementation-pair, product-team, first-project-claude, first-project-mixed and factory-rsi are no longer built in. Rigs you already created from them keep restoring.

    #864Link

  • ChangedTwo rigs with near-identical names no longer end up sharing Docker containers by accident, because each new rig with services gets its own Compose project. Existing rigs keep theirs, and a brand-new rig won't reuse old containers unless you name the project.

    A new rig with services gets a Docker Compose project named from its rig ID instead of its name, so two rigs whose names sanitize to the same string no longer share containers. Existing rigs keep their project.

    A rig created fresh, not as a same-name replacement, won't attach to containers or volumes under the old name-based project unless you set services.project_name.

    #481 · thanks @dajiaohuangLink

  • ChangedIf a new rig's services fail to boot or none of its agents launch, OpenRig takes down the containers it just created and never deletes their volumes. When rigs being replaced would clash over containers, rig up refuses before starting anything.

    If service boot or every agent launch fails, a rig's new Compose project is brought down, never with its volumes. When the earlier rigs being replaced use different projects and no project_name is set, rig up refuses with compose_project_conflict and starts no services, and rig down exits 2 when it keeps a project that a live rig of the same name still uses.

    #481 · thanks @dajiaohuangLink

  • ChangedPreviewing the starter or factory team ends with the same three-team choice, so you can compare before you pick.

    rig specs preview starter and rig specs preview factory end with the three-team choice.

    #884Link

  • ChangedEverything a bundled team brings, from skills and plugins to context packs, is put in place before its agents start, and anything that can't be routed is reported instead of silently dropped.

    Skills, plugins, workflow specs, context packs and agent images in a bundle are put in place before any agent launches, and routing failures are printed instead of dropped.

    #692, #705, #720, #722Link

  • ChangedInstalling a team never changes a context pack you already have under the same name. OpenRig tells you it kept yours.

    Installing a bundle never overwrites or merges into an installed context pack with the same name; it reports already_installed or kept_existing.

    #694Link

  • ChangedBootstrapping from a .rigbundle file now uses the same install path as rig bundle install, so both ways of installing a team behave alike.

    rig bootstrap <file>.rigbundle now goes through the normal bundle install.

    #709Link

  • RedesignedThe built-in teams are now a shorter list with plainer names: starter (a builder and a reviewer) for a first team, factory (a lead and six other agents) for bigger work, and specialist teams such as code-review and research.

    The built-in teams have new names. The shelf is now starter (a Claude Code builder and a Codex reviewer), factory (a lead, an advisor, a builder, QA, design and two reviewers), the specialist teams code-review, research and pm, plus secrets-manager and the kernel. Shipped help, skills and onboarding use the new names.

    #864, #866, #868Link

  • FixedEvery bundle now records which configuration it was built from and the OpenRig version that built it, so you can tell later where it came from.

    Every rig bundle create records the configuration ID and the assembling OpenRig version in bundle.yaml, and bundles built by an installed OpenRig record its real version.

    #718, #708Link

  • FixedInspecting a bundle before you install it now applies the same archive safety checks install does, so an unsafe archive is caught at the first look.

    rig bundle inspect refuses the same unsafe archive entries that install refuses.

    #695 · thanks @DeryFerdLink

  • FixedAn older-format bundle whose project settings point outside its own folder is now refused.

    A legacy bundle whose project block escapes its root is refused.

    #716 · thanks @DeryFerdLink

  • FixedA package can no longer use a skill or agent name to write files outside its install folder. It's refused before anything is written.

    Installing a package whose manifest gives a skill or agent a name that would write outside the install target is refused before anything is written.

    #725 · thanks @DeryFerdLink

Context & skills 16

  • AddedA project can name the world packs its agents should install, alongside the rest of its context.

    A project can list world packs under install.worlds.

    #691Link

  • AddedAny Claude Code or Codex session, even outside an OpenRig team, gets a way into OpenRig by adding one skill with a single npx command.

    The rigs skill gives an ordinary Claude Code or Codex session a route into OpenRig. It lives in the GitHub repository rather than the package; add it with npx skills add mvschwarz/openrig --skill rigs.

    #872, #881Link

  • ChangedImplementer and QA agents now start without the test-driven-development skill loaded. If your team works that way, the skill is still available.

    The implementer and QA agents no longer load the test-driven-development skill by default. The skill is still available.

    #864Link

  • ChangedOpenRig no longer hides the guidance files it adds to your repository: a new CLAUDE.md or AGENTS.md shows in git status, and OpenRig prints the exact ignore line if you want it hidden. Only its Codex plugin files are ignored automatically, in a marked block you can edit.

    Files a launch creates now show in git status. When a launch creates a new guidance file such as AGENTS.md or CLAUDE.md in a Git repository, OpenRig leaves it visible to Git and prints the exact line you can add to .git/info/exclude. New files under .codex/plugins/openrig-core/ are excluded automatically, in a marked OpenRig block in info/exclude where deleting a line makes that path visible again.

    At launch, OpenRig runs your git to check generated files and may append its marked block to info/exclude.

    #721, #727Link

  • ChangedWith several projects in one workspace, an agent loading its project context gets one picked by clear rules and is told how it was chosen. Only a real tie stops it, with a ready-to-run command for each candidate.

    With several projects declared and no --project, rig context work-install picks the project whose rigs: list names the agent's rig, then the deepest project root containing the working folder, then the only unclaimed project, and reports how it chose. It stops with project_required only when more than one still matches, printing a ready-to-run command for each candidate.

    #690, #688, #772Link

  • ChangedThe getting-started and agent help guides now cover what to do when an agent needs attention at startup, including Claude's bypass warning, slow-starting agents and the auto permission policy.

    The getting-started guide and the agent help guide explain rig seat continue, startup attention, readiness timeouts, Claude's bypass warning and builtin:auto.

    #779Link

  • ChangedAdding context works even when the daemon is stopped, because the command starts it for you.

    rig context add starts a stopped local daemon.

    #784Link

  • ChangedAgents working on OpenRig's own code are pointed to the skill that explains how OpenRig is built.

    The bundled skills index sends agents that are changing OpenRig itself to the developing-openrig skill.

    #829Link

  • ChangedIf you read or contribute to OpenRig's code, its developer docs were refreshed throughout, with each claim checked against the code at the time.

    The developer documentation was refreshed, with each claim checked against the code at the time: the README, CONTRIBUTING, SUPPORT and SECURITY; the reference pages for specs, projects, bundles, operations and process; the architecture pages and CLI reference; and ARCHITECTURE, DESIGN and the TUI README.

    A final pass against the release commit is a separate change.

    #782, #777, #783, #785, #788, #789, #791, #795, #797, #823, #825, #775, #778, #781, #787, #790, #792, #793, #794, #799, #804, #805, #826, #856, #796, #803, #806Link

  • ChangedOpenRig's contributor guidance now asks whether an agent with instructions could do a job before anyone writes code for it.

    The contributor skill asks whether an agent with instructions could do a behaviour before adding code for it, and points to the capability map first.

    #827, #828Link

  • FixedSkills that come in a plugin, including OpenRig's own, are now copied to the folders Claude Code and Codex actually load skills from, which never happened before. Checked with stand-in harnesses, and existing agents get them when next created, not on restore.

    When an agent's profile selects a plugin, such as openrig-core, its skills are now copied into the agent's .claude/skills/ or .agents/skills/ folder, where Claude Code and Codex actually load them. Before, neither runtime saw them.

    Checked with stand-in harnesses; whether a real Claude Code or Codex agent lists and loads each skill is checked separately. Existing agents get the skills when they're next instantiated, not on restore. An existing folder with the same name that OpenRig doesn't own is kept, with a plugin_skill_kept warning.

    #815, #823Link

  • FixedThe attention view, the health readout and rig mode effective now use the projects you configured and pick a task's project the same way project context does, so they agree on which project a task belongs to.

    rig mode effective, the attention view and the health readout now read the project catalog you configured, and when a task names only its mission they pick its project the same way rig context work-install does.

    #693, #712Link

  • FixedAn agent can carry its own version of a skill: the launch uses it and warns that it differs from OpenRig's catalog, instead of failing.

    When a profile selects a skill from its own agent folder that differs from the managed catalog, the launch uses the selected skill with a skill_bundle_precedence warning instead of failing.

    #720, #722Link

  • FixedA context-pack folder created in the workspace after the daemon started is now found by sync, without restarting the daemon.

    rig context sync finds a workspace context-pack folder created after the daemon started.

    #686Link

  • FixedContext packs that include JavaScript or Python helper files now install from the command line.

    Context packs with .mjs or .py helper files install from the CLI.

    #706Link

  • FixedSkills and commands no longer point you to skills OpenRig doesn't ship, and rig compact-plan names the compaction restore skill that does.

    rig compact-plan points to the shipped claude-compaction-restore skill, and shipped skills no longer point to skills that don't ship.

    #683Link

Setup & platform 17

  • AddedWhen you want ongoing work, the operator keeps track of it in OpenRig's workspace, not in your repository. A one-off question is simply answered.

    For continuing work, the operator records one mission, and one piece of work under it, in OpenRig's workspace rather than in your repository. A question just gets an answer.

    Guidance for the agents, checked by first-user runs.

    #865Link

  • AddedWhether setup finishes ready, incomplete or as a dry run, it ends by telling you how to reach the operator.

    rig setup prints how to reach the operator after ready, incomplete and dry-run results.

    #859, #886Link

  • AddedAfter install, the agent that installed OpenRig opens the kernel's dashboard, advisor and operator in a new terminal space, so you can see them without disturbing its own session. It's guidance that agent follows, and in the first-user test the person still needed help attaching terminals.

    After installing, the agent opens a new terminal space with the kernel's TUI, advisor and operator, using herdr, then cmux, then a plain terminal window, without taking over its own terminal.

    This is guidance for the installing agent. In the first-user test the person was still guided to attach a terminal five times, which counts as help.

    #821Link

  • AddedIf you work from the repository, an optional script checks for Node and npm, installs OpenRig and runs setup, stopping at the first failure. It isn't in the npm package and isn't documented yet.

    The repository has an optional scripts/install.sh that checks for Node and npm, runs npm install -g @openrig/cli, runs the installed Node.js and SQLite check, then rig setup --dry-run and rig setup, and stops at the first failed step.

    It isn't part of the npm package and isn't documented yet.

    #832, #841, #853Link

  • ChangedAfter upgrading the CLI, restart the daemon so it actually runs the new version. On that first start it also installs the updated openrig-core plugin, which your agents pick up the next time they launch.

    Restart the daemon after upgrading the CLI: run rig daemon stop, then rig daemon start. The running daemon keeps its old build until it restarts, and on its first start it installs the updated bundled openrig-core plugin, which running agents pick up when they next launch.

    #685, #829Link

  • ChangedThe kernel's operator is the agent that installs and runs teams for you, so kernel agents now launch with the broad permissions that job needs, and Codex runs there without a sandbox. If you'd rather keep the old behaviour, set an explicit permission choice.

    Agents in the built-in kernel rig launch with wider permissions by default, so its operator can install and run teams for you. Claude Code runs in acceptEdits with an allow list for file tools, reads under your home folder and operational commands such as rig, tmux, npm, git, ssh and curl; Codex runs unsandboxed with approvals off. rig seat status reports the source as the kernel operational default.

    Applies only when no explicit permission choice, member or rig policy, or (for Codex) named profile is set; set one to keep the previous behaviour. Your ask and deny rules still apply to Claude Code.

    #820, #858Link

  • ChangedAsk your coding agent to install OpenRig and it now hands your goal and project folder to the operator, and leaves the kernel running, instead of building the project itself. Part of that guidance lives on openrig.dev's install page.

    An agent that installs OpenRig for you now keeps the kernel running and passes your goal and project folder to the operator, instead of building the project itself.

    Part of the guidance for an agent finishing an install is on openrig.dev's install page, not in the package.

    #873Link

  • ChangedWhen the operator suggests the workshop, it checks the latest pinned version instead of trusting a cached copy that may be older. This is a text change, and a fresh first-user run hasn't yet confirmed it finds the current workshop.

    When the operator offers the workshop, it reads the workshop's current pinned version from the registry's raw file, because a cached copy can be older.

    A text change, packaged without a new journey run. That a fresh first-user run then finds the current workshop hasn't been reproduced.

    #900Link

  • Changedrig doctor no longer gives a blanket all-clear, so a clean run isn't mistaken for a working setup: it points you to its warnings and says it doesn't check provider logins or agent readiness.

    rig doctor no longer ends with "System checks look good." It says there were no failures, to review WARN and SKIP results, and that provider logins and agent readiness aren't checked.

    #855Link

  • ChangedSetup shows you what to do next before it asks about permissions, and scripts reading its JSON output get the next steps too.

    In rig setup, the guided next steps now come before the permission-policy menu, and --json output gains nextSteps.

    #886Link

  • ChangedWhen setup runs into problems, you get a list of what failed and how to fix each one.

    When rig setup finishes with problems, it lists each failed step with its fix.

    #842Link

  • ChangedStarting without the kernel now tells you the operator won't be running either, and how to start it later.

    rig daemon start --no-kernel and rig start say the operator is skipped too, and how to start it later.

    #873Link

  • ChangedSetup offers to show you the kernel before you pick a team, and treats saying no, working over SSH or running headless as fine.

    Setup's next steps offer the kernel view before you pick a team, and treat declining, SSH and headless use as valid.

    #859Link

  • ChangedCommon install snags on Linux are now in the README and getting-started guide: a system Node.js that's too old, npm 11 skipping the install check, and cmux being optional and macOS-only.

    The README and getting-started say a Linux distribution's own Node.js can be too old and how to install 22 or 24, that npm 11 may skip the postinstall check, and that cmux is optional and macOS-only.

    #839Link

  • ChangedContributors install exactly the dependency versions in the lockfile, so everyone builds against the same set.

    Contributor setup uses npm ci.

    #714Link

  • FixedIf you run OpenRig on Linux, the kernel's advisor no longer talks to you as if you're on a Mac. A community contribution.

    The kernel's advisor agent no longer assumes you're on macOS.

    #770 · thanks @adampogLink

  • FixedA setup dry run on Linux now reports the Homebrew and cmux steps as skipped, so the preview matches your system. A community contribution.

    On Linux, rig setup --dry-run reports the Homebrew and cmux steps as skipped.

    #769 · thanks @adampogLink

OpenRig 0.6.5Run Oh My Pi seats, answer agents with Slack buttons, and keep long Claude sessions going with restore maps.11 added2 expanded13 changed1 redesigned23 fixed

17 contributors · Release notes

Highlights

  • AddedOh My Pi joins Claude, Codex and Pi as a runtime a team can use. Each Oh My Pi agent gets its own home, config, skills and sessions.

    A rig spec can declare runtime: omp to run Oh My Pi seats, each with its own home, config, skills and sessions.

    No live authenticated session against a real provider was run. rig seat clear-attention can't yet recover an OMP seat after a full restore; use rig up --existing <rig> --fresh <seat> instead.

    #35 · thanks @MelonSmasherLink

  • AddedAgents can ask you for a decision in Slack with buttons, up to four questions at once, and the work waits for your tap. A typed reply still works.

    A decision sent to a person in Slack can carry one to four questions, each shown as a row of buttons. A typed reply in the thread still works.

    A Slack app created from an older manifest must turn on Interactivity by hand, or the buttons do nothing. Tested against a simulated Slack, not a live workspace.

    #195 · thanks @sahiljadhav7Link

  • RedesignedBefore a long-running Claude agent's context is compacted, OpenRig asks it to write a map of what matters and waits for it, and afterwards the agent reads its own map back. It's how an agent picks its work back up after losing most of its working memory.

    Managed Claude compaction now asks the seat to write a restore map first, and waits for it before sending /compact, up to 25 minutes for automatic compaction. If no map arrives, that attempt stops instead of compacting an unprepared seat.

    Not tested against a real Claude compaction. When no map arrives, automatic compaction stays off for that seat until you run rig compact again.

    #610, #633, #645, #591Link

  • AddedEach agent in a team can think as hard as its job needs: a planner at high reasoning effort and builders at low, Claude and Codex alike, declared once in the rig spec.

    Each seat can have its own reasoning effort. Put effort on a pod member, in a profile's preferences or in an agent's defaults, and OpenRig passes it to Claude as --effort and to Codex as model_reasoning_effort on fresh launch, resume and fork.

    OpenRig doesn't check the value, and Pi seats ignore it.

    #320, #681 · thanks @shravansumanthananLink

  • FixedOpenRig follows the conversation each Claude agent is actually in, even after /clear. Shut the team down at night, bring it back in the morning, and each agent returns to the conversation it was really in.

    After /clear, rig down and rig up now bring a Claude seat back to its current conversation, not the one from before the clear. At shutdown OpenRig reads the live Claude process's session and saves its current ID.

    Shutdown can take slightly longer. A conversation change in the moment between that read and shutdown hasn't been verified.

    #658Link

Also in this release 45

Seats & restore 7

  • ChangedWith dozens of agents running, the daemon checks on all of them in a few batched tmux calls instead of one or more per agent, so it stays responsive as teams grow.

    Activity, identity and structural sweeps read tmux in a few batched calls instead of one or more per seat, so large fleets stay responsive.

    #293, #309 · thanks @korallisLink

  • ChangedBefore a reboot or upgrade, rig restore-check tells you whether a rig would really come back, because it runs the same checks a restore runs, against the snapshot a restore would use.

    rig restore-check now checks the real queue store and each seat's selected Claude hooks, and runs the same pre-checks a restore would run against the snapshot it would use. A rig spec it can't locate reads as yellow, not checked, instead of red.

    #328, #636, #631 · thanks @dajiaohuangLink

  • ChangedIf tmux can't be reached, rig down no longer forgets a rig whose agents might still be running. It says what it couldn't confirm and keeps the record.

    rig down keeps a rig it can't confirm is gone. If tmux can't be reached, it says so, keeps the rig record and blocks --delete.

    #513 · thanks @Nikhi00718Link

  • ChangedIf you're watching an agent in tmux when its session ends, you're detached instead of being switched into another agent's session.

    Ending a seat's session detaches any terminal viewing it, instead of switching that terminal to another session.

    #187 · thanks @vanducngLink

  • FixedA damaged snapshot no longer stops a restore; OpenRig skips it.

    Restore skips damaged snapshots, and picks the newest of snapshots or checkpoints saved in the same second.

    #207, #206, #601 · thanks @rudycelekli, @shravansumanthananLink

  • FixedSeats with similar names, such as dev and dev-2, can't be mixed up when one of them stops, because OpenRig addresses tmux sessions by exact name.

    OpenRig addresses tmux sessions by exact name, so a seat whose session ended can't be confused with another whose name starts the same way.

    #449, #614, #625, #515 · thanks @rudycelekli, @NishilRathodLink

  • FixedAgents that take around 20 seconds to start are given the time, instead of being marked as failed.

    A seat that becomes ready after about 20 seconds now starts within the 30-second readiness allowance.

    #530 · thanks @xiangzuodalaoLink

Queue & messaging 6

  • AddedWork handed between agents goes through a queue that survives restarts, and a write that times out can now be checked and retried by its ID without creating the work twice.

    rig queue create picks the item's ID before sending and prints it, so after a timeout you can check that exact item and retry with the same ID instead of creating a duplicate. A same-ID retry with a different body warns that the new body wasn't saved.

    #495Link

  • AddedSend work to a seat name with a typo and you get a warning naming the seat you probably meant, instead of a task nobody picks up.

    A queue write to a seat that doesn't exist in a known local rig still goes through, with a warning that names the likely typo.

    #337 · thanks @rudycelekliLink

  • ExpandedYou can hand an agent work from your own terminal, without being an agent in a seat.

    rig queue create --source works from a plain shell outside a seat, recorded as a self-declared source.

    #440 · thanks @rudycelekliLink

  • FixedOpenRig delivers messages by typing them into each agent's terminal and pressing Enter. It now uses tmux's named Enter key, so messages no longer sit typed but unsent when extended-keys is on.

    Typed and pasted text is submitted with tmux's named Enter key, so it no longer sits unsubmitted when extended-keys is on.

    #540 · thanks @Totopo27Link

  • FixedWhen an agent is stuck at a permission prompt, OpenRig doesn't type over it. It raises one alert to the orchestrator or to you, and the agent's work resumes once the prompt clears.

    Work blocked behind a prompt is escalated as one alert to the orchestrator or operator, without typing into the blocked seat, and its wake retries resume once the prompt clears.

    #619, #644Link

  • FixedAgents can't wake themselves, so OpenRig keeps timers that wake waiting work later. Those timers now hold even when the work around them is claimed, finished or set aside again.

    A watchdog attached to a parked queue row survives the other row's claim, completion or re-park.

    #505 · thanks @Vaishnavi220506Link

Claude 6

  • ChangedBefore typing into a Claude agent's terminal, OpenRig confirms the native Claude process and the exact conversation it expects. When it can't confirm a resumed conversation, it reports it as unverified instead of claiming it came back.

    OpenRig confirms a managed Claude seat behind a shell wrapper or a native install from the native Claude process and its exact saved conversation ID, in restore, readiness and identity checks and in rig seat clear-attention. Acknowledging a seat's attention no longer reports its conversation as resumed without strict proof.

    #264, #335, #520, #554, #652, #651 · thanks @dajiaohuangLink

  • ChangedIf you've customised Claude's status line, OpenRig leaves it alone.

    OpenRig keeps your own Claude status line instead of replacing a custom command in .claude/settings.local.json, and no longer wipes that file when it doesn't parse.

    A seat that keeps its own status line doesn't run OpenRig's collector, so its context usage reads as unknown and resume-token capture is skipped.

    #497, #500Link

  • FixedSeveral Claude agents can run under one login and one config folder and each keep its own conversation. Before, two of them could come back in each other's conversation after a restart.

    Claude seats that share a config folder no longer pick up each other's conversations, because a fresh launch records the session ID OpenRig assigned.

    Forks still look the session up by name.

    #656Link

  • FixedIf you start Claude through a launcher shim, OpenRig now finds the real Claude behind it, so messages and queue wakes get through.

    rig send and queue wakes reach a Claude seat whose launcher shim starts the real Claude binary.

    #567 · thanks @Coder8124Link

  • FixedIf a Claude agent's startup message is left typed but unsent, OpenRig presses Enter once more and carries on with a warning instead of failing the launch.

    OpenRig presses Enter once more when a Claude startup prompt is still visibly staged, and starts the seat with a warning instead of failing the launch.

    #598Link

  • FixedWhen a Claude agent has used up both of its usage limits, OpenRig shows when it can actually work again.

    When both Claude usage limits are used up, provider usage reports the later reset time.

    #455 · thanks @rudycelekliLink

Codex 3

  • AddedTwo OpenRig installs can live side by side on one machine, each with its own Codex home, so a test install's Codex conversations stay apart from your main one.

    Each OpenRig install can have its own Codex home. Set an absolute CODEX_HOME when you start its daemon, and managed resume uses that home; with it unset, installs still share ~/.codex.

    Before upgrading, align a CODEX_HOME set in your shell rc with the daemon's, or a Codex seat may not find an earlier conversation.

    #638Link

  • ChangedCodex agents running in their default sandbox can now reach OpenRig's daemon on your machine, so they pick up and hand off queue work like any other agent. OpenRig only adds the network setting when your own Codex config hasn't made a choice.

    Codex seats can now reach the local daemon under OpenRig's default workspace-write sandbox, so they can do their queue work. OpenRig turns on network inside the sandbox only when you haven't made your own choice and no managed requirement restricts it.

    Not checked with real logins, managed policy bundles or on Linux. To keep it off, set network_access = false under [sandbox_workspace_write] in your Codex config.

    #608Link

  • FixedOpenRig tells whether an agent is idle by reading its screen, and now reads recent Codex versions correctly, so idle Codex agents get their work.

    Codex 0.157 and 0.158 seats showing the empty-composer placeholder are recognized as idle, and a busy seat whose status row sits far above the composer isn't misread as idle.

    #295 · thanks @korallisLink

Pi 1

  • FixedPi agents with long launch commands start correctly, instead of having the command cut off by the terminal.

    Long Pi launch, fork and resume commands run from a temporary script instead of being cut off by the terminal's line limit.

    #212 · thanks @rudycelekliLink

Slack 3

  • AddedAgents keep follow-ups about one piece of work in the same Slack thread, and attach their evidence there, including screen recordings and PDFs.

    A follow-up can go into an earlier Slack thread, and video and PDF evidence files up to 50 MiB are attached.

    Tested against a simulated Slack, not a live workspace.

    #155, #298, #305 · thanks @sahiljadhav7, @korallisLink

  • ChangedOn a busy queue with Slack connected, each sweep skips work for items with nothing to post, and usage lookups use an index. Both are based on work by a user running their own large setup.

    Slack sweeps skip building expensive queue views for items with nothing to post, and each seat's latest usage sample is found through an index instead of by sorting its history. Both are based on korallis and Lee's work in korallis/agent-stack.

    On a synthetic 200-row queue the Slack sweep was much faster when few items needed a post, and about 11% slower when none had been posted.

    #642, #569 · thanks @korallisLink

  • FixedTwo Slack messages sent at the same moment in different channels both reach their agents.

    Slack messages in different channels with the same timestamp are both delivered, and retries search up to 10 pages of history for an earlier post with an unknown outcome.

    #452, #395 · thanks @dajiaohuang, @rudycelekliLink

TUI 2

  • ChangedYou can open a second TUI on the same install without it taking control away from the first.

    A second TUI on the same OpenRig home binds its own control socket and shows its path, instead of taking over the first one's.

    #205 · thanks @rudycelekliLink

  • FixedThe TUI copes with a flaky connection to the daemon, and arrow keys work in more terminals.

    The TUI's live activity updates back off when the stream keeps dropping and retry when it's slow to open, and arrow keys work in application-cursor mode.

    #380, #546, #429 · thanks @rudycelekliLink

CLI & hosts 10

  • AddedOpenRig works by watching every agent's terminal. rig ps --resources now shows what that watching costs your machine, and idle agents are watched less often.

    rig ps --resources shows load per CPU, running seats and what transcript capture costs your host. Idle panes are captured less often, and changes to transcripts.lines and transcripts.poll_interval_seconds reach running seats without a daemon restart.

    An idle seat's transcript can trail its pane by about 6 seconds. Load average isn't CPU use.

    #556, #624, #536 · thanks @rudycelekliLink

  • ChangedWhen the daemon refuses a request, these commands now fail instead of printing an empty success, so the scripts and agents built on them see the problem.

    Commands that used to print an empty or successful result when the daemon refused the request now exit 1 or 2, including rig bootstrap, rig env status, rig plugin list, rig context list, rig specs ls and rig start --all.

    #202, #382, #577, #578, #426, #476, #284 · thanks @rudycelekli, @oodadoudouLink

  • ChangedOn very large installs, rig health gives a partial answer for the busiest families instead of failing, and names any source it couldn't read.

    rig health above 200 families evaluates the 200 busiest and marks the result PARTIAL instead of failing, and a failing health source is named as unavailable while the others still report.

    #357, #626Link

  • FixedOpening a project's execution view no longer makes the daemon wait on Git, and transcripts no longer grow by repeating the same line.

    Execution views no longer freeze the daemon while their Git checks run, and a repeated session-boundary line no longer grows a transcript on every capture.

    #557, #545 · thanks @rudycelekliLink

  • FixedThe daemon can run on an IPv6 address, and the CLI and host list work with it.

    CLI commands, the daemon's own endpoints and rig host list work with an IPv6 daemon host.

    #461, #509, #398 · thanks @lab1207, @Totopo27, @rudycelekliLink

  • FixedWhen the daemon is slow to answer, rig status and similar commands say it didn't respond, instead of telling you it's stopped.

    rig status, rig start and four other commands say when the daemon didn't respond, instead of calling it stopped.

    #349, #437, #439 · thanks @Totopo27, @rudycelekliLink

  • Fixedrig ps counts agents stuck at a permission prompt in each rig's attention total, so you can see who's waiting for someone.

    rig ps counts a seat stuck at a pane-only permission prompt in the rig's attention total.

    #180 · thanks @nvtoan0201-sweLink

  • Fixedrig usage top shows missing usage data as unknown, so it isn't mistaken for an agent that used nothing.

    rig usage top lists seats with missing counters as unknown instead of zero.

    #582 · thanks @rudycelekliLink

  • FixedTwo agents editing the same mission no longer silently overwrite each other's changes.

    rig scope refuses a stale mission edit instead of silently dropping another edit, and refuses a slice that depends on itself.

    #339, #286 · thanks @rudycelekliLink

  • Fixedrig daemon stop finishes promptly even while something is still listening to its live events.

    rig daemon stop ends open event streams after a short grace period instead of timing out on them.

    #324 · thanks @dajiaohuangLink

Specs & bundles 3

  • AddedYou can check a rig spec anywhere, on a laptop or in CI, without a daemon running, using the same validators the daemon uses.

    rig spec validate runs locally, with the same validators the daemon uses, so you can check a spec without a running daemon.

    rig spec preflight still needs the daemon.

    #566Link

  • ExpandedAn agent spec can use a plugin from your OpenRig home, wherever that home is.

    Agent specs can point at a plugin with openrig-home:plugins/<name>, and built-in agents load openrig-core from a custom OPENRIG_HOME.

    #620, #627Link

  • FixedA rig can start services such as a database alongside its agents, and OpenRig waits until every replica is healthy before treating them as ready.

    Service readiness accepts bracketed IPv6 targets and requires every Docker Compose replica to be healthy.

    #215, #218 · thanks @rudycelekliLink

Context & skills 3

  • AddedAn agent joining a project can find the project's intent, context files and skills itself with one command, instead of waiting to be told.

    Agents learn the route to your project's context. The onboarding text and bundled skills teach rig context work-install, which lists what the current project declares: its intent, context files and skills.

    #679Link

  • AddedIf you want to contribute, your own agents can load a skill that explains how OpenRig is built.

    Contributors get architecture maps, a developing-openrig skill and a roadmap.

    #282, #539Link

  • ChangedSeveral agents can work in the same repository and each know its own role, without writing their roles into a shared CLAUDE.md or AGENTS.md.

    Kernel seats no longer write their role into a shared CLAUDE.md or AGENTS.md. A startup file can be marked orientation: role, and rig queue whoami --json tells a seat where its role file is.

    #562Link

Setup & platform 1

  • ChangedAgents keep talking to the daemon that launched them, even if your shell startup files point OPENRIG_URL or PATH somewhere else. One less way for a seat to end up on the wrong install without anyone noticing.

    Your shell startup files no longer change a seat's OpenRig settings. Each launch re-applies the daemon's OPENRIG_URL, OPENRIG_HOME and related settings, and puts the rig that matches the running daemon first on PATH.

    For classic Claude launches, a claude alias or function defined only in a nushell rc doesn't resolve, and neither do some older fish setups.

    #618Link

OpenRig 0.6.4The web interface is off by default, and the daemon checks where each request comes from.5 changed19 fixed

7 contributors · Release notes

Highlights

  • ChangedOpenRig's web UI is now off by default. The terminal UI and the CLI are how you use OpenRig, and both are built so agents can drive them as well as people.

    The web UI is off by default. The CLI and the TUI are the supported ways to use OpenRig; the web UI is in maintenance mode.

    To turn it back on, run rig config set ui.enabled true, then stop and start the daemon.

    #303Link

  • FixedShut a team down completely and bring it back, and Claude agents running in auto mode take messages again once OpenRig confirms the same Claude process is in each pane. If it can't confirm the conversation came back, it asks you instead of starting a new one.

    After a full down and up, a managed Claude seat resumed in auto mode takes ordinary messages again once OpenRig confirms the same Claude process is running in its pane. A resume it can't confirm asks for your attention instead of starting a fresh conversation.

    A restore can still report a problem with a seat that works.

    #287Link

  • FixedWork that's waiting keeps its wake-up timer when its seat is handed over to a new agent.

    A blocked queue row keeps its park timer through a seat handover, and a rerouted row's periodic timer is retired.

    #242 · thanks @korallisLink

  • FixedCodex agents in an OpenRig team can use providers other than OpenAI.

    Codex readiness works with providers other than OpenAI.

    #222Link

  • ChangedAgents joining a team read onboarding text that covers how builds go wrong, and learn that a project, rig or machine can add its own skills.

    The onboarding text new seats read now covers both ways a build goes wrong, and the skills router says a project, rig or machine may add its own skills.

    #303Link

Also in this release 19

Seats & restore 4

  • ChangedWhen OpenRig can't verify which runtime an agent is using, it says so instead of reporting the agent as stopped.

    An agent runtime OpenRig can't verify is reported separately from a stopped agent.

    #240Link

  • FixedA rig with a single agent can be relaunched fresh, even when stopping that agent shut down its tmux server.

    A rig's only seat can be relaunched fresh with rig seat launch --fresh --stop, even after stopping it ended the tmux server.

    #267Link

  • FixedWhen OpenRig restores an older Claude agent and can't tell whether its conversation came back, it keeps the new session and asks for your attention instead of closing it.

    If the resume check can't tell whether an older Claude seat's conversation came back, the restore keeps the new session and asks for attention instead of closing it.

    #346Link

  • FixedA launch that times out is reported as an unknown outcome, because the agent may still be starting.

    A seat launch that times out reports an unknown outcome instead of a failure.

    #191 · thanks @oodadoudouLink

Claude 2

  • FixedStarting several Claude agents at once no longer trips a one-second check: OpenRig now gives Claude five seconds to answer before a managed launch.

    Claude's capability check, run before a managed launch with an explicit permission mode, gets five seconds instead of one, which helps when several seats start at once.

    A timeout can still refuse the launch.

    #271 · thanks @m3ac-AllbrittenJLink

  • FixedOpenRig finds a natively installed Claude behind its shell wrapper, including versioned install paths. When it can't see the runtime, messages still go through with a warning.

    OpenRig recognizes a native Claude install behind its managed shell wrapper, including versioned install paths. When it can't observe the runtime, ordinary delivery goes ahead with a warning.

    #310 · thanks @dmeloLink

Codex 1

  • FixedRemoving OpenRig's Codex activity hooks leaves the rest of your Codex configuration as it was.

    Removing Codex activity hooks leaves the rest of your Codex config untouched.

    #186 · thanks @hobostayLink

Slack 1

  • FixedLong messages you send to agents from Slack now arrive whole; before, anything past 1,800 characters was lost.

    Slack keeps a long message from a registered person whole, where anything past 1,800 characters used to be lost, and a storage error during retries is logged instead of escaping.

    Checked with synthetic connections on Linux, not a live Slack test.

    #404 · thanks @rudycelekliLink

CLI & hosts 6

  • FixedIf you start the daemon on a different port, your other commands now talk to that daemon instead of looking for the default one.

    A daemon started with rig daemon start --port is now the one your other local commands talk to.

    #266Link

  • FixedReplacing a proof file swaps in a new file, so a linked artifact somewhere else is no longer overwritten along with it.

    rig proof add --replace swaps in a new file, so a symlinked or hard-linked artifact no longer overwrites the other path's contents.

    #307Link

  • FixedA CLI command's deadline now covers the whole response, and a reply cut off partway is reported as an unknown outcome instead of a success.

    CLI request deadlines cover the whole response, and a body that fails after its headers is reported as an unknown outcome.

    #201 · thanks @rudycelekliLink

  • FixedOutput passed between machines over SSH and rsync, and through Herdr, keeps multi-byte characters such as accents and non-Latin scripts intact.

    SSH, rsync and Herdr output keeps UTF-8 intact across chunks.

    #230, #241 · thanks @rudycelekliLink

  • FixedFiles OpenRig edits keep their executable bit, so scripts stay runnable.

    Atomic file edits keep the executable bit.

    #235 · thanks @rudycelekliLink

  • Fixedrig env status tells you when a service's last result is out of date, so you don't take it as current.

    rig env status says when a service receipt is stale.

    #232 · thanks @rudycelekliLink

Specs & bundles 2

  • ChangedImporting a rig over a stopped one with the same name archives the old rig and tells you how to bring it back.

    Importing YAML over a stopped rig with the same name archives the old one and shows its ID and the command to unarchive it.

    #196Link

  • FixedA bundle of agents keeps binary files exactly as they were, so packaged images and other assets arrive intact.

    rig bundle create keeps binary files in agent packages intact instead of re-encoding them.

    #257Link

Setup & platform 3

  • ChangedThe daemon now checks which address and which web page a request comes from. Your CLI, TUI, agents, Slack and other OpenRig hosts are unaffected; a custom hostname or a local web app needs one setting.

    The daemon checks which address and which web page a request comes from. Nothing changes for the CLI, the TUI, agents, the queue, Slack or other OpenRig hosts; a custom DNS name or proxy domain goes in OPENRIG_ALLOWED_HOSTS, and a local app on another port in OPENRIG_ALLOWED_ORIGINS.

    It isn't complete browser isolation, so keep the daemon on loopback or your tailnet. Both settings need a daemon restart.

    #358, #372Link

  • FixedAfter an upgrade removes the old version, agents still launch, because they use the running version's built-in startup files.

    Seats launch after an upgrade removes the old version, using the running version's built-in startup files.

    #269 · thanks @m3ac-AllbrittenJLink

  • FixedAgent process checks give the same answer whatever language your system is set to.

    Native process checks no longer depend on your locale.

    #239Link

OpenRig 0.6.3This patch repairs a 0.6.2 regression that refused messages to running Claude Code seats launched with an explicit permission mode.1 changed3 fixed

6 contributors · Release notes

Highlights

  • ChangedAgents can attach screenshots and other binary evidence to their proof with rig proof add --media, and existing proof isn't overwritten without --replace.

    rig proof add refuses binary files given as artifact text and asks for --replace before overwriting. Attach screenshots and other binary evidence with --media.

    #177 · thanks @agammann, @korallisLink

Also in this release 3

Seats & restore 2

  • FixedRepeated snapshot attempts no longer leave unusable helper sessions behind.

    A newly created snapshot helper is cleaned up when its input target can't be established and its ownership can still be proven, so unusable helpers stop piling up.

    #189 · thanks @z4ccLink

  • FixedArchived rigs no longer get in the way of a live rig with the same seat names, and removing a stale duplicate keeps the live agent's session and queue work.

    Archived rigs no longer interfere with seat references, and removing a stale duplicate node keeps another live seat's session and queue work.

    #181 · thanks @FarkinellLink

Claude 1

  • FixedMessages reach a running Claude agent even when OpenRig's managed launch puts a shell wrapper in front of it. A pane that's only a shell is still refused.

    rig send reaches a running Claude Code seat launched with an explicit permission mode, even when OpenRig's managed launch leaves a shell wrapper in front of it. A bare shell alone is still refused.

    The process checks used synthetic process metadata; an installed Claude send on every platform wasn't demonstrated.

    #220 · thanks @dmeloLink

OpenRig 0.6.2Choose your providers, give an owner one useful change in your repository, and have a second agent check the result.2 added2 expanded1 changed10 fixed

9 contributors · Release notes

Highlights

  • AddedStart with a small team that does one useful thing in your repository: one agent makes a change and a second checks it. Choose two Codex agents, two Claude agents, or Claude making the change with Codex checking it, using accounts you already have.

    Three first-project recipes give you a small owner and checker team: two Codex agents (first-project), two Claude Code agents (first-project-claude), or a Claude owner with a Codex checker (first-project-mixed). Use the accounts you already have.

    #147Link

  • ChangedA bundled team installs into the project folder you choose and runs from there, so its working directories and files keep working after setup.

    Version-2 bundles copy their verified contents into --target and launch from there, so relative working directories and agent references survive after extraction. Without --target, rig up <file>.rigbundle installs into your current directory.

    #146Link

  • FixedOpenRig delivers messages by typing them into a terminal, so it now refuses to type into a pane it can see is a bare shell where an agent should be running. The message isn't run as shell commands.

    Message delivery won't type a message into a bare shell when an agent runtime should be running there, so it isn't run as shell commands.

    #150Link

  • ExpandedClaude agents can be pointed at an Anthropic-compatible gateway through OpenRig's provider settings.

    ANTHROPIC_BASE_URL can be forwarded through configured provider-auth environment forwarding, so Claude seats can use an Anthropic gateway.

    #143 · thanks @FenjuFuLink

  • FixedIn a project with both Claude and Codex agents, one set of shared skills reaches both, and your edited Codex copies are kept.

    In mixed Claude and Codex projects, shared skills are also placed where Codex looks for them, and edited Codex skills are kept unless you force an overwrite.

    #162 · thanks @a4w-h4yLink

Also in this release 10

Seats & restore 4

  • ExpandedHerdr gets hints about which agents are Claude and which are Codex, and a seat missing its startup context is flagged for attention.

    Known Claude and Codex runtime hints are passed to Herdr, and a missing fresh startup context or adapter is reported as needing attention.

    #106, #107 · thanks @dajiaohuangLink

  • FixedAfter a tmux or host restart, launches find the right terminal by name instead of an old pane.

    Managed launches after a tmux or host restart keep the named launch target instead of confusing it with an old pane binding.

    Actual reboot and power-loss recovery were outside this fix's verification.

    #151 · thanks @diaztunjanoLink

  • Fixedrig restore-check looks in the shared-docs folder you configured.

    rig restore-check uses the configured shared-docs root.

    This doesn't repair every case in #130.

    #139 · thanks @jbaehovaLink

  • FixedWhen a sweep runs slowly, the daemon no longer piles up overlapping polling work on every tick.

    Identity and transcript polling no longer start overlapping work on every tick when a sweep runs slowly.

    This prevents piled-up overlap; it isn't a measured overall CPU reduction.

    #169 · thanks @korallisLink

Queue & messaging 1

  • FixedMessages from this machine's own agents are recognised as local even when the sender names this host.

    A sender qualified with this daemon's own host ID is recognized as a local seat, avoiding false ownership refusals.

    #144 · thanks @korallis, @Yi-111-aLink

Claude 1

  • FixedClaude usage-limit reset times are read correctly when Claude reports them as numbers.

    Numeric Claude rate-limit reset timestamps are accepted.

    #108 · thanks @dajiaohuangLink

Codex 1

  • FixedCodex agents launched through a managed shell wrapper receive messages and queue nudges.

    Messages and queue nudges reach a ready Codex seat launched through a managed shell wrapper instead of being refused as a bare shell.

    #171Link

Pi 1

  • FixedPi agents keep line editing in terminals that report themselves as TERM=dumb.

    Pi seats keep line editing with TERM=dumb.

    #123 · thanks @shravansumanthananLink

CLI & hosts 1

  • FixedOpenRig reads tmux window details reliably, and tells health it didn't ask for apart from a health check that failed.

    tmux window fields with printable separators parse correctly, and health that wasn't requested is no longer reported as a failed read.

    #101, #102 · thanks @dajiaohuangLink

Setup & platform 1

  • AddedThe agent setting up OpenRig asks you once whether OpenRig's own commands can run without repeated permission prompts, and changes nothing if you say no.

    Agent-guided setup asks once whether to allow OpenRig commands without repeated permission prompts. Yes adds native rig command rules at project scope, or user-wide if you choose, without granting general shell access.

    The scope, loading and revocation of these rules weren't yet verified in this release.

    #147Link

OpenRig 0.6.1Get help from your installed version with one command, and launch from linked Git worktrees.2 added1 expanded5 fixed

6 contributors · Release notes

Highlights

  • AddedThe help guide is written for your agent: ask it to run rig context get help and it works through environment checks, setup problems and permissions itself.

    One help path: ask your agent to read rig context get help for environment checks, setup and restart symptoms, permissions, instance layout and escalation. If rig can't run, the same guide is online at openrig.dev/help/agents.

    #113Link

  • AddedEvery pull request now runs eight test jobs, including a scenario with a deliberately planted lost-work failure that the checker has to catch.

    Pull requests now run eight test jobs, including an installed queue-durability scenario with a deliberately planted lost-baton failure that a checker must catch.

    It doesn't certify every platform, provider or authenticated agent workflow.

    #117Link

Also in this release 6

Seats & restore 1

  • FixedOn machines not set to UTC, OpenRig compares an agent's activity against the real start of its session.

    On hosts not set to UTC, identity and context-usage readers compare observations with the real start of a seat's generation.

    #124 · thanks @Coder8124Link

Codex 3

  • FixedOpenRig recognises when a Codex agent is at its conversation prompt and ready for input, including just after a dismissed hook-review panel.

    Startup and resume checks recognize Codex's » conversation prompt, including a fresh prompt after a dismissed hook-review panel.

    #111 · thanks @dajiaohuangLink

  • FixedCodex agents with a custom status line are still recognised once their header has scrolled away.

    A Codex conversation is recognized when its header has scrolled away and a custom status line puts the model name after other fields.

    Recognition only; the separate stale restore warning in #116 isn't repaired here.

    #125 · thanks @Hexgunner69, @AummadourLink

  • FixedCodex agents can be launched from linked Git worktrees.

    Codex fresh launches work from linked Git worktrees, resolving the worktree's Git directory instead of treating its .git file as a directory.

    #126 · thanks @mgall-ibizdigitalLink

CLI & hosts 1

  • ExpandedYou can open the execution view for any catalogued project by naming it, not only for the default workspace.

    rig view show execution reads a catalogued project's execution view when you name its --project and --mission.

    It doesn't infer the project from your current directory.

    #105 · thanks @dajiaohuangLink

Context & skills 1

  • FixedThe bundled Vault skill loads cleanly, and shipped skills are checked for valid headers.

    The bundled Vault skill has valid frontmatter, with a check for shipped skill headers.

    #115Link

OpenRig 0.6.0Set each agent's permissions, open a whole team at once, and turn on a guard that holds automatic input while you type.5 added3 changed2 fixed

5 contributors · Release notes

Highlights

  • AddedEach agent in a team can run under its own audited permission level, such as a locked-down reviewer beside a builder with full bypass, set for its future launches.

    Choose permissions per seat: rig seat set-permissions records an audited choice for that seat's future launches, floor, full_bypass or inherit. Claude modes such as auto are accepted only when the seat's Claude advertises them.

    Native enforcement across fresh launch, resume and fork wasn't verified. Status output doesn't prove a mode's effective permissions; check the running session.

    #109Link

  • AddedOne action in the TUI opens every running agent in a rig as tabs in Herdr.

    Open a whole rig in Herdr from the TUI. Every running seat opens in a workspace named after the rig, up to 16 seats per tab.

    Check that the rig opened as expected in your Herdr version.

    #109Link

  • AddedYou can work in an agent's terminal yourself while OpenRig holds that agent's automatic messages in an outbox, so nothing types over you.

    A typing guard for seats where you type by hand. It pauses all automatic input to that seat and keeps messages and wakes in an outbox, which you read with rig seat held-messages.

    It covers OpenRig's own input paths, not other tools writing directly to the terminal.

    #109Link

  • FixedA seat outlives the agent sitting in it: OpenRig tracks which agent is in a Pi seat and ignores activity reports from an earlier one.

    Pi seat activity reports carry the seat's occupant generation, and reports from an earlier or foreign generation are refused instead of being attributed to the seat.

    Activity reporting from an installed Pi seat wasn't verified end to end.

    #109Link

Also in this release 6

Queue & messaging 1

  • AddedAn optional, experimental classifier can label your agents' stream of observations, using Jev through OpenRouter. It's off unless you turn it on.

    An optional classifier seat can have Jev, through OpenRouter, label Rig Stream observations. It's off by default and runs only when the classifier seat runs one foreground command.

    Experimental. The labels are advisory, with no demonstrated accuracy, and nothing routes on them.

    #109Link

Codex 1

  • ChangedEach Codex agent's tools run in its own app-server instead of one shared between agents.

    Codex seats launch with --no-daemon when the installed Codex supports it, so each seat's tools run in its own app-server instead of a shared one.

    #77 · thanks @reisalbuquerqueLink

Slack 1

  • AddedYou can create OpenRig's Slack app in your own workspace from a manifest OpenRig prints offline, before any daemon or token exists.

    rig slack manifest prints the Slack app manifest for the app you create in your own workspace, offline, before any daemon or token exists. --url gives Slack's create-app link with the manifest filled in.

    Experimental. The setup steps haven't been confirmed against a real app creation.

    #109Link

CLI & hosts 1

  • FixedMissions and slices created with rig scope no longer trip the readiness check when they have no metadata block.

    Missions and slices created with rig scope no longer fail the readiness reader when their manifest has no metadata block.

    #91 · thanks @shravansumanthanan, @kainne44Link

Setup & platform 2

  • ChangedOpenRig moves to Node.js 22 or 24. If you're on Node 20, switch Node and reinstall; your data stays put and is upgraded in place.

    OpenRig now requires Node.js 22 or 24 and uses better-sqlite3 13. Node 20 is refused with an explanation, and your data stays where it is: the daemon reopens the same database and applies pending migrations in place.

    Node 26 and odd-numbered Node versions aren't supported or tested. On Apple silicon, use Node.js 22.

    #16 · thanks @jimallenLink

  • ChangedThe kernel starter tells you when it's showing a preview, that the runtime is picked for you, and which agents are actually running.

    The kernel starter's summary says when it's showing the library preview, explains that the runtime is chosen automatically, and points to the seats actually running.

    #109Link