OpenRig Files

OpenRig 0.7.10 is a patch for people running their own agent teams. A step held after a managed compaction now goes in instead of waiting forever. Sends get through a pane in any tmux mode. rig exec runs a queue task on Claude Code or Codex as one finite run. Installs try a user-writable npm prefix first, and spec advisories show at launch. There are fixes across refocus, routing, status and speed, many from people using OpenRig. The OpenShell worker now does real work and exports results, but its cleanup still fails against OpenShell 0.1.6, so don't rely on cleanup or recreate yet.

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.

Before you upgrade

:::bash
npm install -g @openrig/cli@0.7.10
rig daemon stop && rig daemon start

• There are no migrations.
• 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.
• 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.
• OpenShell users: rebuild the guest image with this release's guest.py (see daemon/assets/openshell/README.md).

What's new and fixed

Finite runs.

• 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, #2596)

Compaction, delivery and terminals.

• 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. (#2576)
• Delivery leaves every tmux mode, and a refusal says why. (#2594)
• A stale record naming a reused tmux pane no longer stops a send from leaving the mode. (#2644)
• Writable views size the pane they show. (#2614)
• 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. (#2634)

Coordination and status.

• 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)

• Refocus names a trace gap instead of failing (#2582, #2587).
• The stuck sweep stops filing informational updates to people as unclaimed work (#2586).
• rig slack status counts cross-host relays in flight (#2569).
• rig seat status shows a Claude seat's latest permission request, with suggested rules labelled. Nothing is applied or approved. (#2562)

Install, specs and errors.

• The rigs skill tries a user-writable npm prefix or a version manager's Node before a project-local install. (#2611)
• 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. (#2613)
• Spec advisories show as launch warnings and never stop a launch, and an unknown uses key gets one. (#2606, #2585, #2618)
• 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)

Speed under load.

• 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)

OpenShell.

• 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. (#2602)
• 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). (#2603)

Docs and tests. Codex named profiles (#2604), openrig-core skill loading (#2584), what the runner contract has run (#2592, #2595), telemetry's guarantee beside the separate, untested openrig-telemetry exporter (#2589), and a real-tmux test that waits for the prompt (#2559).

Behaviour that changed

• A held post-compaction step goes in over an unreadable box, so an unrecognised draft may receive the restore text.
• Sends leave any tmux mode a person has open.
• rig up can print advisory warnings.
• 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.

Known issues

• 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.

The full list of limits, including those carried from earlier releases, is in CHANGELOG.md. Its 0.7.10 section was written before testing, so where it and these notes differ, these notes have the tested result. In particular, its statement that both OpenShell problems are fixed in the source is out of date: the owned-environment cleanup fix doesn't hold against OpenShell 0.1.6.

Credits

Thanks to @dajiaohuang, @Aummadour, @billbenetti, @smota, @Nikhila-Dhevi-R and @Vaishnavi220506 for merged contributions. Thanks 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 thanks to @billbenetti, @KM199, @ziadeh, @dajiaohuang, @jajabong, @george661 and @aanestesia for reports carried into this release, and to @smota for the OpenTelemetry discussion behind #2589.