`agentproto maintain`
text agentproto maintain [--repo <dir>]... [--all] [--apply-merged] [--apply-reviewed] [--review-preset <name>] [--wait] [--json]
agentproto maintain
agentproto maintain [--repo <dir>]... [--all] [--apply-merged] [--apply-reviewed] [--review-preset <name>] [--wait] [--json]Convenience shortcut over agentproto workflow run-file for the built-in
repo-maintenance app's
maintain workflow. Needs a running daemon (agentproto serve) — unlike
branch gc and worktree gc, the workflow's
review step spawns real agent sessions.
One run:
- Plans
worktree_gc,branch_gc, andsandbox_checkpoint_gc(dry run — nothing is touched; the checkpoint plan classifies the staleagentproto-checkpoint/*refs a dead sandbox left on the remote as safe / keep / unknown). - Fans a reviewer agent out over the unmerged branch candidates with no
stored verdict yet — at most
maxReviews(default 40) per run, newest tip first, so daily runs walk a large backlog — one turn per unique tip sha: a small model when the candidate's residual is 3 files or fewer, a large model otherwise. Each turn records a verdict viabranch_gc_verdict— recording a verdict never deletes anything. A turn that ends without a stored verdict gets one same-session re-prompt, then one large-model retry. A reviewer model role's configuredprofileandrouteride the spawn too (access.profileRef/route), so anopencode-go/...reviewer can bill a named profile instead of ambient auth. Branches held only because they're checked out in a linked worktree join the queue too, when that worktree is idle (no live session), clean, has no open PR, and its tip is at least 3 days old. Otherwiseworktree gcandbranch gcwould each hold them forever. The report lists each such worktree's verdict, plus theagentproto worktree rmcommand when the reviewer agreed nothing of value is lost. Removal stays manual. The workflow inputreviewHeldWorktrees: falseturns this off. - Re-plans
branch_gcto confirm every candidate got a verdict, and reports any gap, the verdict tally, and thesalvagebranches by name. - With
--apply-merged: appliesbranch_gc(reclaim-class only by default),worktree_gc, andsandbox_checkpoint_gc(stale checkpoint refs; the engine re-plans and re-classifies every ref immediately before deleting it). Adding--apply-reviewedruns the branch apply withincludeReviewed: true, so areview-class branch whose stored verdict agreed for the same tip is reclaimed too.branch_gcstill enforces its deterministic line-coverage guard (default 95%): an approval below it is refused (refused-guard) and listed in the report's "Human decision queue" with its coverage percentage. Without--apply-reviewed, areview-class branch is never reclaimed. - Reports a markdown summary.
Verdicts are recorded with branch_gc_verdict, which also accepts an
operator: { by, note? } block. A reviewer verdict under the line-coverage
guard is refused by branch_gc; an operator approval for the same tip sha is
the human exit from that queue and lets includeReviewed reclaim it despite
the guard (the plan shows verdictGuard: bypassed by operator <by>). The
maintain workflow applies with includeReviewed: $input.applyReviewed —
false unless --apply-reviewed is passed (with --apply-merged), so by
default it records and reports verdicts but never deletes a review-class
branch.
| Flag | Default | Description |
|---|---|---|
--repo <dir> | cwd | Any dir inside the repo. Repeatable — pass multiple --repo flags to target specific repos. Combined with --all to supplement discovered repos. |
--all | false | Run once per repo: every main repo that owns a worktree under the worktrees root, plus any --repo dirs. Prints the discovered repo list first; exits 1 if any run fails. |
--apply-merged | false | Apply (reclaim-class only) after review. When used with --all, applies to every repo. |
--apply-reviewed | false | With --apply-merged, also reclaim review-class branches whose stored verdict agreed (includeReviewed: true). branch_gc refuses approvals below its line-coverage guard (default 95%) and reports them; ignored without --apply-merged. |
--review-preset <name> | daemon modelRolePreset | Reviewer model set for this run: opus, sonnet, haiku, go-free, free-sonnet (see modelRolePreset). Each reviewer spawns on the adapter its model needs, so go-free runs on opencode. |
--wait | false | Block until each run ends, then print its markdown report. Exit 0 when all done, 1 when any failed or was cancelled. |
--json | false | Print the raw workflow_run_file reply (with --wait: the finished run records, one per repo). |
This starts the run and returns immediately (the run executes in the background) — poll it with:
agentproto workflow status <runId>Or pass --wait to block until it finishes and print the report inline.
Examples
# Plan + review only, nothing deleted
agentproto maintain --repo ~/code/my-app
# Plan + review, then apply reclaim-class branch/worktree gc
agentproto maintain --repo ~/code/my-app --apply-merged
# Also apply agreed reviewed branches (line-coverage guard still applies)
agentproto maintain --repo ~/code/my-app --apply-merged --apply-reviewed
# Run for every repo that owns worktrees under the worktrees root
agentproto maintain --all --apply-merged
# Block until done and print the report
agentproto maintain --repo ~/code/my-app --waitScheduling it
packages/apps/repo-maintenance/routines/ ships two AIP-41 ROUTINE.md
templates targeting the same maintain workflow, both enabled: false:
repo-maintenance-daily (plan + review, no apply) and
repo-maintenance-weekly (applyMerged: true + applyReviewed: true; drop
applyReviewed to keep the weekly apply reclaim-class only). See that
directory's README for how to enable one per workspace.
`agentproto llm`
text agentproto llm endpoints list [--json] agentproto llm endpoints test [--json] agentproto llm endpoints add <name> --url <baseUrl> [--connector <id>] [--api-key-env VAR] [--json] agentproto llm en
`agentproto mcp-app`
text agentproto mcp-app <appId> agentproto mcp-app --http <appDir> [--port N] [--host H] [--tenants <file.json>]