Skip to content

fix(skills): respect disabled approval setting - #7617

Merged
NicholasRBowers merged 1 commit into
kirodotdev:mainfrom
rubencu:fix/respect-disabled-skill-approvals
Sep 12, 2026
Merged

NicholasRBowers merged 1 commit into
kirodotdev:mainfrom
rubencu:fix/respect-disabled-skill-approvals

Conversation

@rubencu

@rubencu rubencu commented Sep 1, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

With skills.approval_required=false, a generated auto-skill candidate whose supplied scripts ALL fail static validation was still staged for review. The user had opted out of approval requests, yet a New skill awaiting review notification arrived anyway — for a candidate whose executable content had been entirely discarded, saved as if it were a prose-only skill.

Why it matters

The Settings UI says approval is off while approval requests keep coming. Worse, the staged candidate hides what it was: it attempted to ship executable content, every script was rejected by the validator, and it now sits in the queue disguised as harmless prose. The notification even offers to disable a setting that is already disabled.

What changed (motivation → approach → change)

An all-invalid-scripts candidate is now rejected outright when approval is disabled. The staging decision in HistoryConsolidator._process_auto_skills gains a reject branch: a candidate that supplied scripts, kept none through validation, and has no review queue to land in (approval off) is dropped as a whole — logged and SEL-audited with reason all_scripts_rejected — instead of being staged against the user's opt-out or auto-published. The staging elif reads self._approval_required or valid_scripts: the reject branch consumes the one case where a bare scripts_supplied used to decide, so that disjunct is gone.

This fix deliberately covers NEW candidates only. UPDATE candidates for live skills always stage for human review regardless of approval_required — an update overwrites a live skill, and approve_pending_update is the only path to live — so the opt-out does not apply there and that path is unchanged.

Both prior safety boundaries hold. A candidate that retains any valid script still stages (only the passed scripts are kept). An all-invalid candidate still stages when approval is enabled, so a human can inspect the prose. A script-bearing candidate still never auto-publishes live. The owning spec bullet (docs/system-specs/modules/memory-skills-hooks.md, "Staged approval") is updated in the same commit to name this third outcome.

Tests

  • test_all_invalid_scripts_are_rejected_when_approval_disabled: an all-invalid-scripts candidate with approval off produces no live skill and no pending review entry.
  • Adjacent coverage in TestProcessAutoSkillsIntegration keeps proving that with approval enabled the prose still stages and the dangerous script is dropped.
  • Mutation proof: with the production rejection hunk reverted, the regression test fails (prove.py PROVEN).
  • isort, flake8, mypy, docs lint, and the targeted test files pass locally; full backend suite green except failures that reproduce identically on pristine main (host-environment only).

Manual verification

N/A — unit coverage exercises script validation, live-skill creation, and pending-queue behavior directly.

Related Issues

No linked issue: reported directly from observed dashboard behavior.

Pattern harvest

Rule candidate: review-prompt
Pattern: a candidate whose executable payload was entirely rejected must not be re-classified as benign prose; the rejection must follow the candidate, not the payload.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title (feat|fix|docs|refactor|perf|test|chore|ci|build|revert: ...)
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (the owning spec bullet in docs/system-specs/modules/memory-skills-hooks.md names the new rejection outcome)
  • No secrets, credentials, or internal references in the diff

@rubencu
rubencu requested review from a team and krishdhasmana September 1, 2026 11:59
@github-actions github-actions Bot added fork Pull request from a fork (external contributor) readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running and removed readiness: action required A blocking check or review needs attention labels Sep 1, 2026
@github-actions

github-actions Bot commented Sep 1, 2026 •

Copy link
Copy Markdown
Contributor

GPT 5.6 Review (fork) — ✅ no blocking findings

Reviewed 047d51cee4cafe819599770a0cf1b5dbbf830763 via the fork AI-review pipeline; updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 047d51c

@github-actions

github-actions Bot commented Sep 1, 2026 •

Copy link
Copy Markdown
Contributor

Opus 4.8 Review (fork) — ✅ no blocking findings

Reviewed 047d51cee4cafe819599770a0cf1b5dbbf830763 via the fork AI-review pipeline; updated in place on each push.

Review details

The working tree is at main (54fa0ed), not the PR HEAD, so the diff file is authoritative for the change. Let me verify the staging branch still emits an observable SEL audit and confirm the case table.

The relevant code and diff are clear. Let me trace the candidate's claim carefully.

The new logic:

  • approval_required=False, scripts_supplied=True, valid_scripts=[one] (mixed): branch 1 (scripts_supplied and not valid_scripts and not approval_required) is skipped because not valid_scripts is False; branch 2 (self._approval_required or valid_scripts) fires → stage_skill_candidate.

So the mixed candidate stages into pending even with approval disabled. Now testing outcome (c):

  1. The design intent, restated in the doc hunk and the branch comment, is explicit: "a script-bearing candidate never auto-publishes." Staging a candidate that carries a validator-passed executable script — rather than auto-publishing it as prose — is precisely the guarantee, not a violation of it. Auto-publishing executable content without review is the harm being avoided.

  2. The claimed outcome "never surfaces / no one drains the queue" is false. The pending queue is drainable via the dashboard (Skills → Pending review) independent of approval_required; approval_required=false only enables prose-only auto-publish, it does not disable the pending queue.

  3. The claimed "no SEL audit making it visible" is false: the stage branch (lines 2100–2110) emits an outcome="staged" SEL event, so it is observable.

The candidate's own confidence is "low" and concedes "this is arguably the intended trade-off." Under falsification, outcome (c) does not hold — the behavior is the documented, audited, intended design. Killed.

No further defect exists in the reshaped branch: the case table is complete and consistent (approval on → always stage; prose-only + approval off → auto-publish; all-invalid scripts + approval off → audited reject; mixed/valid scripts + approval off → stage). No crash, no data loss, no removed guard without replacement.

No findings.

[OPUS-REVIEWED] 047d51c

@github-actions

github-actions Bot commented Sep 1, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Fable 5, fork) — ✅ PASS

Premise-level review of 047d51cee4cafe819599770a0cf1b5dbbf830763 via the fork AI-review pipeline — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

All the facts I need are verified. The base else branch at line 2121 auto-publishes live, so simply deleting the scripts_supplied disjunct wasn't a viable smaller fix; the reject branch's SEL audit matches the established reject-audit pattern used four other times in the same function (empty_after_redaction, similar_exists, creation_failed ×2); scripts_supplied has exactly one deciding site; and the rewritten pin's own rationale ("can never auto-publish as a prose-only skill") is preserved by the new assertion list_auto_skills() == [].

First-Principles-Verdict: PASS

Verify one thing: the rewritten "(GPT MEDIUM)" pin — with approval off, the prose learning is now silently discarded (SEL/log only), not queued for salvage.

What this change ships

Inventory (5 items) — 5 justified

Intent: stop approval-off users receiving review requests for candidates whose scripts all failed validation — a FIX.

  1. Approval-off, all-invalid-scripts candidate is dropped outright instead of staged into the queue the user opted out of — justified
  2. The drop leaves a SEL audit record, reason all_scripts_rejected — justified
  3. Spec "Staged approval" bullet names the third outcome — justified
  4. Pin test rewritten from "always stages" to "rejected"; its own rationale (never auto-publish) still asserted — justified
  5. Adjacent test comment now states staging happens because approval is enabled — justified

The pin rewrite carries its evidence: the deleted comment justified staging solely as the means to prevent auto-publish, and the new test keeps list_auto_skills() == []. The UPDATE-candidate path still stages despite opt-out, but that is declared, with a distinct cause (overwriting a live skill), not an unfixed sibling. scripts_supplied had one deciding site (grepped: 3 hits, all in _process_auto_skills), now consumed by the reject branch — cause-level, not symptom.

[FIRST-PRINCIPLES-REVIEWED] 047d51c

@github-actions

github-actions Bot commented Sep 1, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Fable 5, fork) — ✅ PASS

Design-level review of 047d51cee4cafe819599770a0cf1b5dbbf830763 via the fork AI-review pipeline — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Verified the base code matches the diff context; the reject branch consumes exactly the case the removed scripts_supplied disjunct decided, the UPDATE path is untouched as described, and the rewritten test preserves the original pin's stated invariant (a script-bearing candidate never auto-publishes) while honoring the user's opt-out — the spec bullet is updated in the same commit.

Design-Verdict: PASS

A real UX/trust bug fixed at the decision point, with the original no-auto-publish safety pin preserved and spec, test, and SEL audit updated coherently.

[DESIGN-REVIEWED] 047d51c

@rubencu
rubencu force-pushed the fix/respect-disabled-skill-approvals branch from be48b6d to 207ccd3 Compare September 1, 2026 12:40
@rubencu rubencu changed the title fix(skills): hot-reload approval setting fix(skills): respect disabled approval setting Sep 1, 2026
@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention and removed readiness: checking Automated validation is still running labels Sep 1, 2026
@bolichen97

Copy link
Copy Markdown
Contributor

Open PR relationship audit

This is a consolidated, point-in-time code-level audit note. It compares complete merge-base diffs and current/merged code; it does not treat a shared topic as duplication or partial coverage as completion.

Relationship findings

  • This PR is OVERLAPPING with PR #392. The goals differ or the implementations can complement each other; this is not a duplicate claim. Recommended action for PR #7617: MERGE_DISCUSSION. The change reverses a documented, deliberately-commented decision from a merged PR; a maintainer should confirm that dropping the inspectable pending entry is the intended trade rather than a silent loss of the user's only view of a rejected script-bearing candidate. Files: src/kiro_crew/history_consolidation.py.
  • This PR is OVERLAPPING with PR #2713. The goals differ or the implementations can complement each other; this is not a duplicate claim. Recommended action for PR #7617: MERGE_DISCUSSION. Recorded as evidence that the invariant has been reaffirmed more than once in this repo; it imposes no requirement on 7617 by itself. Files: src/kiro_crew/history_consolidation.py.
  • This PR is OVERLAPPING with PR #4533. The goals differ or the implementations can complement each other; this is not a duplicate claim. Recommended action for PR #7617: MERGE_DISCUSSION. No code conflict, but the two open PRs encode opposite answers to the same question — whether a candidate that supplied only invalid scripts must remain inspectable. One rule should be settled before either lands. Files: src/kiro_crew/history_consolidation.py, src/kiro_crew/dashboard/handlers/core.py.
  • This PR is OVERLAPPING with PR #6307. The goals differ or the implementations can complement each other; this is not a duplicate claim. Recommended action for PR #7617: MERGE_DISCUSSION. Independent keys in a shared handler; at most a mechanical rebase, no behavioural interaction. Files: src/kiro_crew/dashboard/handlers/core.py.

No PR, Issue, label, branch, or review state was changed by the relationship-note portion of this audit.

@chenmingwei23 chenmingwei23 added the needs-pr-triage PR scanner: awaiting automated triage label Sep 11, 2026
@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention merge conflict Branch has merge conflicts with its base — author must resolve before merge and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Sep 11, 2026
@NicholasRBowers NicholasRBowers added drive-to-green PR claimed by drive-to-green pipeline and removed needs-pr-triage PR scanner: awaiting automated triage labels Sep 11, 2026
@NicholasRBowers

Copy link
Copy Markdown
Contributor

🤖 Kiro Crew [operator: NicholasRBowers#a942f9ca]: This PR has been inactive for 7+ days with failing CI. I've assessed the blockers and they appear resolvable — I'll push fixes directly to this branch as a co-author.

Assessment: Two blockers, both from a stale base: (1) merge conflict with main; (2) Dependency Audit red on high vulns (fast-uri, js-yaml) in website/electron/package-lock.json that current main has already remediated — other PRs pass this gate today. A rebase onto current main resolves both. GPT/Opus are clean; Design's Watch item (use a public setter on HistoryConsolidator instead of writing the private _approval_required field) is a specific mechanical change I'll fold in, and the advisory CONCERNS verdicts will each get a disposition.

If you'd prefer I don't touch this PR, add the pr-no-autofix label.

@NicholasRBowers
NicholasRBowers force-pushed the fix/respect-disabled-skill-approvals branch from 207ccd3 to 7d356b0 Compare September 11, 2026 11:42
@NicholasRBowers

Copy link
Copy Markdown
Contributor

Intent: When skill approval is disabled, an auto-skill candidate whose supplied scripts all fail validation is rejected outright — never auto-published as disguised prose and never staged into a review queue the user opted out of.
Not a goal: Changing how updates to live skills are reviewed, hot-reloading other config keys, or altering staging behavior when approval is enabled.

@NicholasRBowers NicholasRBowers removed the drive-to-green PR claimed by drive-to-green pipeline label Sep 12, 2026
@rubencu
rubencu deleted the fix/respect-disabled-skill-approvals branch September 12, 2026 15:06
amadsalmon pushed a commit to amadsalmon/KiroCrew that referenced this pull request Sep 22, 2026
When skills.approval_required is disabled and an auto-skill candidate
supplies scripts that ALL fail validation, reject the candidate outright
instead of staging it for a review the user opted out of (or disguising
it as a prose-only skill). The rejection is logged and recorded as a SEL
tool-invocation event, and the staging condition drops the now-dead
scripts_supplied disjunct (the reject branch consumes its only deciding
case). The owning spec bullet in memory-skills-hooks.md is updated in
the same commit to name the third outcome.

Original change by Ruben Cuevas Menendez (rubencu). Rebased onto current
main: the dashboard-handler hot-reload hunk was dropped because main now
hot-reloads skills.* into the running HistoryConsolidator through its own
live.watch_object subscription (reconfigure()), and the accompanying
PATCH regression test was removed as subsumed by
test_services_config_hot_reload.py.

Co-authored-by: Kiro Crew <noreply@kirodotdev.github.io>
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 9, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 9, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 9, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 10, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 10, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 10, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 11, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 11, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 12, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 12, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 15, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 15, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 15, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 16, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 16, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 16, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 16, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 16, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 16, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 17, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 17, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
rubencu added a commit to rubencu/KiroCrew that referenced this pull request Oct 17, 2026
A prose-only update to an existing auto-skill can now be applied without
review when the operator opts in with skills.auto_apply_updates on top
of approval_required=false; disabling approval alone still stages every
update. An update whose supplied scripts all failed validation follows
the kirodotdev#7617 rule: rejected when approval is off, staged as prose when it
is on.

Every promotion, dismissal and unattended apply first captures the
pending generation through authenticated no-follow reads, records its
digest in a held claim lock, renames the public directory into a hidden
quarantine and publishes only from a fresh private materialization of
the captured bytes. Updates publish the complete live tree with
no-replace renames and keep the replaced generation as permanent public
evidence; restart recovery consumes, re-queues or retains each claim by
exact digest and native identity.

The private authority lives at tag-grants/auto-skill-private, beneath a
directory every Kiro Crew sandbox already masked, so no new deny leaf,
mask or spawn check is added and an authority problem never refuses an
agent spawn. Gateway startup provisions it; a refusal only disables
auto-skill staging and promotion. Hosts whose agents run in a sandbox
Kiro Crew does not build never get an authority (fail-closed default).

All auto-skill locks follow one documented order,
skills.AUTO_SKILL_LOCK_ORDER: slug claim, claim, target, namespace.

Fixes kirodotdev#3795
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

fork Pull request from a fork (external contributor)

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants