Changelog

Daemon restart and supervision fixes

Running boss daemon restart could previously kill a running daemon and then fail to bring a new one back up, leaving you with no service at all. That is fixed: Boss now detects which mode the daemon is actually running in before restarting, so it restarts in the right mode and leaves you with a working daemon afterward.

On macOS, boss daemon doctor could also miss cases where the daemon was registered with launchd but would never actually start, then silently fall back to a less reliable unsupervised mode without telling you. Doctor now checks the launch history and surfaces that situation clearly instead of hiding it.

Improvements

• Sessions in the dashboard now lay out more evenly: the repository column takes only as much space as it needs, and the session name column gets the rest.
• Boss can now notify you when an AI session (Codex) is waiting for a reply choice, not just when it is asking a direct question. If a session was paused waiting for you to pick an option, you would not have been told. Now you will be.
• Fixed an issue where sessions could disappear from the list if the daemon serving them reported a different location than expected. Sessions now track liveness against the daemon that owns them, so they stay visible.

Fixes

• Fixed an issue where restarting the daemon could destroy a healthy instance without successfully replacing it.
• Fixed an issue where boss daemon doctor would silently downgrade to unsupervised mode when it could not verify launchd supervision, instead of warning you.

Organization management and invitations

You can now invite people to your organization directly from Boss. Invitations are sent by email, show up in the members table as pending, and can be revoked before they are accepted. When someone accepts an invitation, they are added as a member automatically. The members table and invite form now reflect the real state of each invitation rather than showing a simplified view.

Improvements

• Organizations are now listed alphabetically throughout the product, making them easier to find when you belong to several.
• Cron jobs, connected machines, and accounts are now listed across all of your organizations in one view, with each item labeled by which organization it belongs to.
• When searching to start a Linear session, pressing Enter now takes you straight into the selected issue without an extra confirmation step.
• Boss can now tell when a Codex credential has been rotated by something outside Boss (for example, another tool or a manual change). When that happens, the affected account is marked clearly so you know to reconnect it rather than wonder why it stopped working.
• Boss now distinguishes between a credential whose refresh has not been verified yet and one that is outright broken, so the health check gives you a more accurate picture of what is actually wrong.
• Fixed an issue where a service lookup failure could make an organization’s machine or session list appear empty when it should have shown an error. Boss now tells you when something went wrong rather than silently showing no results.
• Idle Claude chat sessions are now cleaned up correctly in the background. Previously, a session-identification mismatch meant they were never reaped.
• Long session names and error messages in the web session list are now truncated so they no longer overflow the layout.

Fixes

• Fixed an issue where certain shell-level failures were misreported as credential errors. Boss now shows them as unavailable rather than blaming your credentials.
• Fixed an issue where review comments could fail to save correctly when a pull request was updated.
• Fixed an issue where the planning step could lose structured content when passing a plan forward to the build step.
• Fixed an issue where epic time tracking could produce unbounded values when child issues had very long elapsed times.
• Fixed an issue where session data could show organization labels that were not relevant to the page you were on.

Organizations are now a first-class way to group your repositories

You can now assign repositories to organizations directly from the Repositories page, and a single organization selector follows you across every screen that shows repos. Switching organizations filters everything in one step rather than requiring you to reconfigure each view separately.

A data issue that caused some accounts to end up with a duplicate organization record has been repaired. If your account was affected, the duplicate has been merged away and the lockout it caused is resolved.

A few smaller organization fixes shipped alongside this: members can no longer accidentally remove their own membership, entitled users can create organizations without needing extra steps, and the organization picker now hides itself when there is only one choice and showing it would add no value.

Improvements

• Smarter code review. Boss now decides how thorough a review pass to run based on how large the change actually is, rather than using a fixed approach regardless of diff size. Smaller diffs get a lighter pass; larger ones get more scrutiny.
• Reviews finish in fewer steps. Boss now completes a build review in a single review pass instead of stacking multiple passes on top of each other. This makes review runs shorter and the output easier to follow.
• Bot review comments no longer block merges. If Boss has already given a clean review, automated bot review comments are now treated as advisory. They are visible but will not hold up a merge on their own.
• CI checks resolve faster. Boss now reacts to CI status updates as they arrive instead of checking on a fixed timer. Builds and checks that finish quickly will unblock your session sooner.
• Reviews with findings can still be marked ready. When a review hits its cap, Boss now marks the result as ready-to-ship with findings attached, rather than reporting it as blocked. Callers can decide what to do with the findings rather than having the run hard-stop.
• Longer-running child tasks are less likely to time out. Boss now gives sub-tasks within a larger epic more time to complete before treating them as failed, and isolates failures so one slow child does not take down the others.
• Usage limit status is more accurate. Fixed several cases where a connection interruption, a system wake, or a slow startup could leave the account usage display stuck, blank, or replaced by an error screen. Boss now recovers cleanly from all of these.
• boss cost shows review efficiency. The cost report now includes how many review passes a run used and what state it finished in, so you can see at a glance how much of a run’s work went into review.

Fixes

• Fixed an issue where the connection-lost notice and its “Try again” button could become unreachable with a keyboard or screen reader.
• Fixed an issue where dismissing a connection error and retrying could leave the retry button stuck in a disabled state.
• Fixed an issue where creating an organization could leave the name field unfocused or the submit button unresponsive.
• Fixed an issue where a repository with no assigned organization would spin indefinitely in settings instead of showing a clear empty state.
• Fixed an issue where the invite modal’s email field was sized incorrectly relative to its surrounding form.
• Fixed an issue where duplicate status announcements could be made when reconnecting, resulting in redundant screen reader output.
• Fixed an issue where bookkeeping problems could block a run from completing rather than surfacing as a warning and continuing.
• Restarting Boss is less likely to show a false connection error immediately after restart.

Fixes

• Fixed an issue where the terminal could crash with a “Cannot read properties of undefined” error after a session closed, particularly if output or events arrived in the brief window after the terminal shut down.

Usage tracking for agent runs

Boss now records how much work each agent run does, including token usage and cost, across all agent types. This data feeds into the cost diagnostics view, so you can see a clearer picture of where usage is coming from, broken down by run.

Previously archived runs were missing from that view. Boss now imports their data as well, so your cost history is complete.

Improvements

• Cost diagnostics now cover the full run history, including runs that completed before this version.

Review is faster and more accurate

Boss’s code review engine received a significant overhaul in this release. Review rounds that can run in parallel now actually do, and the fix loop between rounds runs in batches instead of one finding at a time. Together these changes cut out large stretches of idle time during review sessions. The review phase ladder was also simplified: what previously stretched into ten sequential rounds, most of them redundant, now collapses into a tighter sequence.

Boss also now writes a durable ledger for each review session. This gives you a reliable record of what was reviewed, which rounds ran, and what each one found, so a skipped or completed round is no longer ambiguous from the outside.

Improvements

• Boss’s review confidence score is now derived from the actual evidence collected by the review panel rather than inferred from the phase alone.
• Review funding (how much effort is allocated to a review) is now derived from evidence rather than estimated up front.
• Both Claude and Codex agents now resolve extensions from the same root, so extension behavior is consistent regardless of which agent is running.
• Boss now records which effort level each agent ran at, so the setting is visible and auditable rather than silently applied.
• When CI check results are evaluated, Boss now uses a single centralized path for reading verdicts, reducing the chance of inconsistent results across different views of the same check.
• Boss can now tell the difference between different kinds of gate failures on the host, making it easier to understand why a gate did not pass.
• Epic child tasks are now classified as live or not using a more conservative rule, so tasks are not incorrectly treated as complete when they have not actually moved.
• Boss-plan now cleans up leftover scratch data from previous runs before starting a new one, preventing stale state from influencing the current run.
• Dependency relationships in plans are now validated more carefully, reducing cases where a blocker edge was inferred incorrectly or oriented the wrong way.

Fixes

• Fixed an issue where Boss’s preflight check would report a command as blocked when it was actually a valid, recognized command.
• Fixed an issue where background gate runs would only report the status of the launcher process, hiding failures in the actual test work.
• Fixed an issue where CI checks could report success even when no meaningful tests had run, due to affected-test selection and caching interactions.
• Fixed an issue where adding a new test file would silently leave the test manifest stale, causing CI to fail in a way that looked unrelated to the change.
• Fixed an issue where cached state in Boss could report stale values for session status, merge blocking, and review gate results after the underlying code changed.
• Fixed an issue where the review triage step would return a clean verdict for findings that were malformed, misattributed, or could not be represented correctly.
• Fixed an issue where epic plan steps could resume from the wrong position after a plan update, or expose child tasks before their preconditions were met.
• Fixed an issue where prose-based gates over skill documentation would pass even if the documented behavior was not actually present in the code.
• Fixed an issue where dispatching subagents in some flows could produce inconsistent or lost results due to a contract mismatch in how awaited agents were handled.
• Fixed an issue where callbacks could be armed or cleaned up unsafely, leading to missed or duplicated transitions.
• Fixed an issue where stale installed skills could run silently when the installed version had drifted from the source. Boss now blocks the run and reports which paths have drifted.
• Fixed an issue where dependency updates could leave related modules with outdated checksums, causing builds to fail unexpectedly.
• Fixed an issue where the review oscillation detector could produce identity collisions, causing distinct findings to be treated as duplicates.

Smarter code review: more accurate, faster, and better at catching late-breaking conflicts

Boss’s code review has been overhauled in several ways this release. The changes work together to make reviews more reliable and less likely to miss something important.

Reviews now apply suggested fixes directly. When Boss identifies a problem in your code, it now produces a concrete patch rather than a freeform description. That means suggestions are easier to apply and less ambiguous.

Each review round focuses only on what changed. After the first pass, Boss reviews the delta since the last round rather than re-reading everything from scratch. This keeps later rounds tighter and more relevant.

Boss now notices when other PRs land mid-review. If a related pull request merges into the base branch while Boss is reviewing your code, it will detect the conflict at each round boundary, attribute it to the right PR, and flag it. Previously, this kind of overlap could slip through to the final push unnoticed.

Fix and confirmation steps now run in parallel. Parts of the review that can proceed independently now do so at the same time, which reduces overall review time.

Improvements

• Boss carries forward observations made during earlier review rounds, so context is not lost between passes. Duplicate notes from round to round are automatically removed.
• Test result caching now keys off the exact state of the code being tested. A cached result is only reused when the code genuinely has not changed, which prevents stale cache hits from masking real issues.

Session recovery is more reliable

Bringing a session back to life after it goes offline could silently fail in a few common situations. Boss now handles these cases correctly:

• Repos with a slow or long-running setup script can be resurrected again. Previously, the setup step could time out in a way that made the session unrecoverable. You now also see live progress while the restore is running.
• Fixed an issue where a session tied to a worktree that had been deleted outside of Boss would refuse to resurrect. Boss now cleans up the stale registration before trying to recreate it.

Improvements

• When Boss is running a code review and the wall-clock time limit is reached mid-fix, it now allows one final round to close any open required fix rather than stopping with the work in an unfinished state.
• Auth tokens for active sessions are now saved to disk, so they survive a Boss restart. Before this, restarting could force sessions to re-authenticate from scratch.
• Restarting Boss is less likely to leave sessions in a confused state after an authentication failure. The failure is now tracked consistently so recovery picks up where it left off rather than resetting.
• Fixed an issue where a session that failed to switch context early in a recovery attempt could still consume part of the session’s retry budget, making future recoveries less likely to succeed.
• Fixed an issue where a 401 error that Boss itself generated internally could be mistaken for an account authentication problem, sometimes triggering unnecessary account rotation.

Fixes

• Fixed an issue where a session could be left with an open required fix after hitting a time limit, which could block merging.
• Fixed an issue where health tracking or chat availability could be incorrectly affected by a recovery attempt that was refused before it even started.

Fixes

• Fixed an issue where a slow or unresponsive agent was reported as “agent not found” during startup checks. Boss now distinguishes between an agent that is genuinely missing and one that simply took too long to respond, so the error message you see reflects what actually happened.
• Fixed an issue where starting Boss after a package upgrade could load an outdated version of its background process instead of the newly installed one. Boss now stages the correct version before launching, so upgrades take effect as expected.
• Fixed an issue where cancelling an operation in certain timing windows could produce a false error instead of a clean exit.

Refresh a single PR on demand

You can now ask Boss to re-sync a specific pull request without waiting for a full background refresh. This is useful when a PR’s status looks stale in the session list and you want it current right away. The operation is available from both the CLI and via MCP.

Features

• boss new --detach reports session details immediately. When you start a detached session, Boss now prints the session ID and setup progress as they happen, so you do not have to wait until setup finishes to know where things stand.
• boss ls --json includes session liveness data. The JSON output now carries when the agent was last active and which tracker is attached, making it easier to build scripts or tools that check session health.
• Settings changes roll back on a failed save. If Boss cannot save a settings change, it now restores the previous value and keeps the settings panel open, so you do not lose track of what was changed or end up with a misleading on-screen state.
• Boss now records when a chat turn starts, which lets it report that timing back to MCP callers.

Improvements

• Credential injection failures are now visible. When Boss fails to inject account credentials into an agent, it surfaces the error in both the CLI and the UI instead of silently falling back to a default login. A health record is also written so you can see what went wrong.
• Login state survives UI rebuilds. A re-login prompt triggered during a session would sometimes disappear when the interface refreshed internally. That state is now preserved across rebuilds.
• Auth error overlays are less jumpy. The “authentication failed” status indicator is now debounced and corroborated before it appears, so transient auth probes no longer cause it to flicker on and off.
• Stale Linear task claims are now forfeited automatically rather than left open, which prevents them from blocking future work.
• When running sessions in parallel, Boss is better at detecting when a claimed task is actually being worked on by a still-active peer before deciding to take it over.
• Epic planning is more resilient: helper state is validated more carefully, recovery from partial failures is cleaner, and plan attachments that have gone stale are replaced rather than left in place.
• PR commit tagging handles edge cases more reliably, including long commit subjects and bootstrap commits.
• Fixed an issue where optional labels in plan and build steps could cause incorrect behavior when the label was absent.
• Boss-repair now groups review thread feedback and verifies gate summaries before acting on them.
• After a rebase, Boss runs integrity checks before continuing, catching drift that could otherwise cause silent build failures.

Fixes

• Fixed an issue where cancelling a session switch could be dropped or reordered, leaving the switch in a stuck state.
• Fixed an issue where planning sessions were incorrectly counted toward deduplication checks meant for regular sessions.
• Fixed an issue where the TUI back button stopped working when an error overlay was open.
• Fixed an issue where duplicate improvement notes could appear across repeated runs of a notes sweep.
• Fixed an issue where a failed settings save would leave the UI showing the new (unsaved) value with no indication that the save did not go through.
• Fixed an issue where the release sweep could not locate the correct binary, causing it to exit early.