Foreman v0.11.0
AI review on the session diff
Hand the diff to a second agent before you read it yourself. Its findings come back as comments on the exact lines they refer to — the same comments you'd write by hand — so you edit the ones that need nuance, delete the ones you disagree with, and send the rest straight back to the agent that wrote the code. One batch, one turn.
- Your model, your effort. Pick both per review, independent of the session's own — a review is a different job from the work being reviewed.
- Choose what gets reviewed. Deselect the files you don't care about, then re-review just the one you fixed. The whole selection still goes in a single pass, so cross-file issues are still found.
- No praise, no summaries. The review only reports things worth changing. If nothing is, it says so.
- Findings it can't pin to a line are shown, not dropped — so a review is never quietly lossy.
- Cancel actually stops it. Started a review on the wrong files? Cancel kills the agent on the spot rather than letting it finish in the background on your bill.
Merge conflicts, resolved in the app
A conflicted merge, rebase, cherry-pick, or revert now shows every conflicted file with the state it's in — and lets you finish it without reaching for the terminal.
- Take a whole side per file, or open a file and go hunk by hunk, keeping either side, both, or an edit you write yourself.
- Sides are labelled Current and Incoming, with the branch or commit git itself named — including during a rebase, where "ours" means the branch you're rebasing onto, not your work.
- Continue the operation once everything is settled, right next to the Abort that was already there.
Scheduled tasks
Foreman can now run an agent for you on a schedule — once at a set time, or on a repeat (every day, or, say, every Monday at 09:00). A scheduled task is just a normal prompt plus a when: point it at a project, write the prompt, pick a cadence, and Foreman launches the session for you when the time comes.
- Runs even when you're away. If a run's time passes while Foreman is closed, it fires the next time you open the app — and is marked "ran late" so you know it caught up.
- Isolated output you review. Turn on "Run in a worktree" and each run lands on its own fresh branch — review the diff and merge it yourself. Nothing touches your main checkout.
- Model & effort per schedule. Choose the model and reasoning effort each schedule runs with, just like a normal session.
- Quiet by default. A run that finds nothing to do finishes silently. You only get a notification when there's an actual change to review — or when a run failed, with the reason (for example, an integration that needs re-authenticating before it can run unattended).
- Run history. Each schedule keeps its recent runs, so you can see how they went and jump back into any of them.
Perfect for a weekly "what's new in the Claude CLI, and should Foreman adopt it?" scan, a nightly repo-health check, or a recurring pass over your issue tracker.
Git & pull-request panel polish
Cleaner layout for the Git and PR panels.
More reliable permission prompts
Fixed a case where a session's permission prompt could fail to initialize, and made plan mode stick correctly when a run auto-continues.
macOS, Apple Silicon. Signed with a Developer ID certificate and notarized by Apple — opens normally with no Gatekeeper warning, and in-app silent auto-update is enabled.