axstack 0.20.19 → 0.20.21

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axstack",
-  "version": "0.20.19",
+  "version": "0.20.21",
   "description": "Axstack installer and setup CLI: installs owned chat skills and role data, configures supported harness settings, and checks Orca capabilities.",
   "keywords": [
     "claude-code",

package/skills/axstack/references/automations.md

@@ -45,9 +45,10 @@ discovery or admission; never infer lane ownership from an empty local workspace
 Bind the lane to the automation ID and pass to its native run ID, workspace ID,
 and terminal identity, not a title or directory-name guess.
 A confirmed live manager for the same lane remains authoritative.
-The new duplicate does no PR work, makes no shared-record write, touches
-nothing owned by the live manager, and closes only its own exact terminal as
-its final action under the guard below.
+Once identified as a duplicate, the new pass does no PR work, makes no further
+shared-record write, touches no live or unsettled resource owned by the live
+manager, and closes only its own exact terminal as its final action under the
+guard below.
 Unknown liveness blocks admission and shared-record writes; it does not
 authorize takeover, cleanup, or a duplicate manager. Preserve `user_takeover`
 and other user-owned sessions.
@@ -119,6 +120,7 @@ PRs cannot starve older unserved work.
 ## Per-PR jobs
 
 At PR-job and reviewer dispatch, apply [Readable sidebar](workspace-hygiene.md#readable-sidebar).
+Include [Safe deletion](workspace-hygiene.md#safe-deletion) in PR-job briefs.
 
 The logical manager lane owns ongoing discovery and continuity across finite
 sessions; the bounded PR coordinator owns only its admitted event. Do not create a second live owner or
@@ -250,7 +252,8 @@ At pass start, clear finished predecessor terminals of the same automation in
 the dedicated workspace only after proving completion, by the exact-handle
 fallback in [Workspace hygiene](workspace-hygiene.md).
 Then run the driver-start orphan sweep for repositories listed in this lane's
-run record, under the same guards. The sweep is silent when nothing was removed;
+run record plus registered repositories on this host containing eligible settled resources
+of any Axstack run on this host, under the same guards. The sweep is silent when nothing was removed;
 record sweep results and holds in the continuity record's Open holds table.
 
 After admission closes, settle every owned PR job and all descendants before the

package/skills/axstack/references/lifecycle.md

@@ -56,7 +56,7 @@ Only an explicit user request to transfer ownership enters this branch.
    prior owner seeing a different valid accepted owner stops.
 
 Complete record: goal, authority, intent, IDs, revisions, evidence, pending
-receipts/timers, unresolved decisions, next action, and transfer ownership/gap.
+receipts/timers, unresolved decisions, next action, and transfer status.
 
 ## Receipts (bind each decision to evidence)
 
@@ -87,8 +87,8 @@ covers only ordinary reading, writing, and local checks. Heartbeat deliveries
 are acknowledged with no user-facing text. Process each whole delivery before
 acknowledgment and validate its Task, Dispatch, sender, authority, revisions,
 and receipts before advancing the run record. Duplicate deliveries are
-deduplicated by runtime identity. Healthy unchanged observations produce no
-user-facing update. After accepting worker, Task, or Run completion, the driver
+deduplicated by runtime identity. Healthy unchanged passes are silent.
+After accepting worker, Task, or Run completion, the driver
 invokes [axstack-cleanup](../../axstack-cleanup/SKILL.md) inline; it never
 dispatches cleanup work.
 
@@ -99,8 +99,8 @@ session liveness, delivery, and verified advancement are distinct evidence.
 On `consumer_fenced`, reconcile the active coordinator rather than borrowing an
 identity. Respect settlement protection including `user_takeover`.
 
-No execution heartbeat or substitute scheduler is created by Axstack. Native
-review automation follows [Review automation health](#review-automation-health).
+Axstack creates no execution heartbeat or substitute scheduler. See
+[Review automation health](#review-automation-health).
 Tracking grants no merge, release, model-substitution, or scope authority.
 
 ## Deadline (one rule for every owned timer)
@@ -131,15 +131,16 @@ nothing without tested independent review.
 
 ## Close-out
 
-PRs merge by forge state—not branch ancestry; close out: (1) settle every worker
+PRs merge by forge state; close out: (1) settle every worker
 terminal; (2) compact record with counts and denominators—user
 interventions/deviations from plan/repairs; (3) `axstack-auditor`: settle
 non-zero/requested, else `counts zero`; an unavailable auditor leaves close-out
 pending, never skipped silently; (4) release merged run worktrees and branches;
-use `axstack-cleanup` and close selected external-tracker tickets when applicable;
+use `axstack-cleanup`, remove the run's own automations under
+[Workspace hygiene](workspace-hygiene.md), and close selected external-tracker tickets;
 (5) mark the
 [Run record](run-record.md) `Archived`. `Archived`—one each:
 settlement receipt; compact record path; auditor decision plus settlement
-receipt or `counts zero`; release and ticket receipts; archive timestamp.
+receipt or `counts zero`; automation, release, and ticket receipts; archive timestamp.
 `active`/receipt-incomplete record: close-out pending, never done. One-step
 lookups exempt.

package/skills/axstack/references/orca-runtime.md

@@ -72,6 +72,8 @@ small-change intent, brief, authority, role snapshot, worktree, base, and
 candidate to the Task; preserve the returned
 Task, Dispatch, terminal, agent, and worktree identities. Exactly one Dispatch
 may write a candidate at a time.
+Put the [Safe deletion](workspace-hygiene.md#safe-deletion) rule in every
+worker brief.
 
 Create a worker worktree with `--parent-worktree` naming the candidate's
 worktree when both are in the same repository; see

package/skills/axstack/references/workspace-hygiene.md

@@ -8,6 +8,15 @@ only report leftovers. Record each decision and native readback in the private
 run record; uncertain ownership, liveness, or evidence
 holds only the affected resource.
 
+## Safe deletion
+
+Every shell deletion targets a literal absolute path or a `${VAR:?}`-guarded
+expansion (for example, `rm -rf -- "${EV:?}/mut"`), only inside the worker's
+own evidence folder, `TMPDIR`, or worktree. Never use a bare `$VAR`, a glob on a
+variable, `/`, `HOME`, or a shared root as a deletion target. Prefer
+`git clean -- <exact prefix>` or tool-native cleanup. A safety prompt that
+still appears is a hold; agents do not answer it.
+
 ## Settlement
 
 At intermediate completion, once a worker or reviewer Dispatch is accepted,
@@ -21,10 +30,11 @@ At final settlement, no eligible non-driver session or worktree remains,
 including the run's worktrees in other repositories. Report each remaining
 resource as a hold with its reason. Recorded native ownership by Run, Task,
 and Dispatch decides; parent/child display lineage does not. The creator closes
-what it created. A finite scheduled pass closes only its own exact terminal as
+what it created at ordinary settlement; the cross-run sweep below may retire
+its settled leftovers. A finite scheduled pass closes only its own exact terminal as
 its final action. Manual chats, automation dedicated workspaces, and genuine
-`user_takeover` sessions are never removed. Deleting a session means closing
-its terminal; agent chat history is not deleted.
+`user_takeover` sessions are never removed by ordinary settlement or sweep.
+Deleting a session means closing its terminal; agent chat history is not deleted.
 
 If native exact terminal close returns `runtime_error` for a provably finished
 agent, send `/quit` + Enter to that exact terminal, wait about 5 seconds, then
@@ -35,6 +45,30 @@ leaves its terminal for the next pass, without treating that expected failure
 as a hold. At pass start, clear only provably finished predecessor terminals
 of the same automation in its dedicated workspace by this exact-handle path.
 
+## Owned automation retirement
+
+At Close-out, reconcile the run record with native inventory: the recorded
+owning Run must have created the exact automation IDs selected for retirement.
+The sweeping pass uses that recorded owning Run, not its own Run, for cross-run
+watches. A cross-run sweep may retire a disabled per-run watch only when its
+owning run is closed or every watched PR is merged or closed. Uncertain recorded
+ownership, watch state, or disable result holds the affected automation.
+
+For each eligible automation, disable it and verify native readback before
+`orca automations remove <id>` on its exact ID, and verify absence by native
+readback. The observer only disables and reports; the driver removes its own
+run's automation. Only a retired owned per-run watch's workspace may be removed
+under these guards. Never remove the durable review manager and its dedicated
+workspace or a user-created automation and its dedicated workspace.
+
+Remove that dedicated workspace only after confirming its exact ownership, no
+live terminal, a clean worktree, and a head on the remote. Recheck ownership and
+liveness immediately before workspace removal. If dirty or unpublished, use the
+salvage and bundle verification below before removal; failed verification or
+uncertain liveness is a hold. The current scheduled pass cannot remove its own
+workspace while its terminal is live; the driver or a later sweep finishes that
+step. Record separate automation and workspace receipts.
+
 ## Preserve before removal
 
 Workers write reports, probes, logs, evidence, and scratch to the private
@@ -59,14 +93,28 @@ removal, and use exact native worktree removal without force.
 
 Drivers sweep on phase-skill entry. A scheduled pass that owns its lane with
 recorded cleanup authority runs the driver-start orphan sweep after predecessor
-terminal cleanup, scoped to repositories listed in its run record. On
-phase-skill entry, scope the sweep to the current repository and the
-per-run worktrees in other
-repositories recorded in the driver's run records. If Orca is unreachable,
+terminal cleanup, scoped to repositories listed in its run record plus
+registered repositories on this host containing eligible settled resources of
+another Axstack run. On phase-skill entry, scope the sweep to the current repository
+and the per-run worktrees in other repositories recorded in the driver's
+run records, and registered repositories on this host containing eligible settled
+resources of another Axstack run. Inspect other Axstack run records on this host
+too; a live owning run does not protect its settled
+reviewer worktree or merged author after preservation checks. If Orca is unreachable,
 report one line and continue the phase; an unreachable host holds only its
-items. This is standing authority to remove an orphan after salvage when every
-owning Dispatch and descendant is settled, ownership and liveness are rechecked
+items. A sweep may remove resources of ANY Axstack run on this host after salvage
+when every owning Dispatch and descendant is settled (completed or failed), its
+release is confirmed or `release_unknown`, no agent is working, the exact terminal
+has had no output for at least 60 minutes, ownership and liveness are rechecked
 from a fresh native list, and evidence is durable. Remove descendants first.
+For a settled worker dispatched into a shared or driver worktree, close its
+exact terminal individually under the same 60-minute quiet rule: native close,
+else the guarded `/quit` + `exit` fallback above. Never close the live coordinator
+session's terminal for any run (the driver's own terminal) or a user chat.
+Align/Spec adviser sessions reused between rounds remain until
+their owning phase approves or stops; the quiet rule still applies then.
+For a merged or closed PR author with an unreleased settled Dispatch, request
+native worker release first, record its result, then apply the sweep guards.
 An author worktree of a merged or closed PR is sweep-eligible when its head
 commit is retrievable from the forge (for example, the PR's recorded head or a
 remote branch contains it); unverifiable state is a hold. For an eligible
@@ -78,6 +126,9 @@ them in its own continuity Open holds table. Both are silent when nothing was re
 Branches with a remote counterpart are never deleted. List live or unsettled
 work, genuine `user_takeover`, and items without provable Axstack provenance in
 one table with their reason; do not remove them.
+Dirty or unpublished work follows the salvage and publication guards above;
+open-PR authors remain protected until merge or close. Record each removed and
+held resource in the pass continuity (scheduled) or run record (driver start).
 
 ## Native bookkeeping exceptions
 
@@ -87,7 +138,9 @@ the run record contains the exact repair Dispatch ID for that terminal;
 otherwise hold. Report the mislabel to Orca upstream through the driver.
 For `release_unknown`, reconcile with native worker inspection. If a fresh
 native terminal list confirms the terminal is gone, record the readback and
-proceed; otherwise hold.
+proceed; otherwise hold unless inspection proves a settled, quiet worker. Then
+close only that worker's exact terminal under the sweep rule and confirm its
+absence. Unknown liveness holds.
 
 ## Known Orca issues
 

package/skills/axstack-cleanup/SKILL.md

@@ -25,7 +25,7 @@ and worktree removal. Do not embed or improvise a competing command protocol.
 ## Authority and scope
 
 Inline cleanup may consider only resources owned by the accepted completion it
-is processing. Driver-start orphan sweeps use the standing authority in
+is processing. Driver-start orphan sweeps follow the guarded cross-run sweep in
 [Workspace hygiene](../axstack/references/workspace-hygiene.md). Backlog
 cleanup requires an explicit bounded selector such as a
 Run, Task set, workspace set, repository, or named age window; age narrows an

package/skills/axstack-implement/SKILL.md

@@ -7,6 +7,7 @@ description: When an approved task is ready to build or repair, use axstack-impl
 
 On driver entry, sweep under [Workspace hygiene](../axstack/references/workspace-hygiene.md); dispatched workers do not sweep.
 For every dispatch brief, name its private `<run dir>/evidence/<dispatch>/` folder.
+Include [Safe deletion](../axstack/references/workspace-hygiene.md#safe-deletion) in author briefs.
 At author dispatch, apply [Readable sidebar](../axstack/references/workspace-hygiene.md#readable-sidebar).
 
 From an accepted scope identity, drive its task/PR map through author -> review

package/skills/axstack-review/SKILL.md

@@ -7,6 +7,7 @@ description: When a candidate PR or bounded codebase needs review, use axstack-r
 
 On driver entry, sweep under [Workspace hygiene](../axstack/references/workspace-hygiene.md); dispatched workers do not sweep.
 For every dispatch brief, name its private `<run dir>/evidence/<dispatch>/` folder.
+Include [Safe deletion](../axstack/references/workspace-hygiene.md#safe-deletion) in reviewer briefs.
 At reviewer dispatch, apply [Readable sidebar](../axstack/references/workspace-hygiene.md#readable-sidebar).
 
 Manual review keeps the user’s chat and workspace open.

package/skills/axstack-watch/SKILL.md

@@ -137,8 +137,9 @@ observed state distinct from merged, and the human merges by default.
 ## 6. End and preserve continuity
 
 End a chat-run watch only after all members merged or closed or user
-cancellation, with own-automation disable/readback and driver-owned cleanup
-receipts in [Watch runtime](references/watch-runtime.md#chat-run-watch).
+cancellation, with own-automation disable/readback and driver-owned automation
+removal and workspace cleanup receipts in
+[Watch runtime](references/watch-runtime.md#chat-run-watch).
 
 End a standalone watch early when all required PRs merge, at cancellation, or
 at its shared default 24 h deadline. In every case, stop all owned

package/skills/axstack-watch/references/watch-runtime.md

@@ -10,7 +10,10 @@ A standalone PR owner remains accountable through the default 24-hour window.
 current GitHub state, persists event IDs, wakes the owner only for a new
 actionable event, and never sends or mutates. Healthy observations update
 quietly. Reuse prior watch identity rather than registering a duplicate, and
-stop task-owned registrations at completion, cancellation, or expiry.
+stop task-owned registrations at completion, cancellation, or expiry. The owner
+must disable and read back its own automation, then remove it by exact ID under
+[Workspace hygiene](../../axstack/references/workspace-hygiene.md#owned-automation-retirement).
+Remove its dedicated workspace only after the terminal and preservation guards pass.
 
 ## Chat-run watch
 
@@ -52,8 +55,10 @@ recorded cleanup authority acts as its lane's driver: clear only proven
 finished predecessor terminals of the same automation in its dedicated
 workspace, using the exact-handle fallback in
 [Workspace hygiene](../../axstack/references/workspace-hygiene.md), then run
-the driver-start orphan sweep for repositories listed in its run record under
-the same guards. Recorded cleanup authority is separate from and does not imply
+the driver-start orphan sweep for repositories listed in its run record plus
+registered repositories on this host containing eligible settled resources of
+any Axstack run on this host, under the same guards.
+Recorded cleanup authority is separate from and does not imply
 repair or maintenance authority. That cleanup-authorized watch pass is silent
 when nothing was removed and records sweep results and holds in its continuity
 Open holds table.
@@ -107,8 +112,11 @@ Stop only when all members merged or closed, or on user cancellation recorded
 by the driver in the run record. Re-read membership and confirm no ambiguous
 publication or unsettled pass; cancellation
 prevents new work but does not prove running workers exited. The observer may
-disable only its own automation and must verify native disable/readback. A
-failed or uncertain disable is a hold. Report the stop receipt to the driver.
+disable only its own automation and must verify native disable/readback. A failed
+or uncertain disable is a hold. Report the stop receipt to the driver; the
+driver removes the automation by exact ID, verifies absence, and removes the
+dedicated workspace after the observer terminal closes under
+[Workspace hygiene](../../axstack/references/workspace-hygiene.md#owned-automation-retirement).
 The driver separately settles workers, preserves evidence, and archives the run;
 an unavailable driver leaves those steps pending. The standalone 24-hour expiry
 and peer observation contracts are unchanged.