Skip to content

Scope generated files during reviews #29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
gustavonline merged 1 commit into from
Oct 12, 2026
Merged

Scope generated files during reviews #29

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion VERSION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
0.1.12
0.1.13
14 changes: 12 additions & 2 deletions adlc/factory-review/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,8 @@ name: factory-review
description: Independently assess a concrete candidate against its accepted scope, project standards and actual verification evidence before delivery.
license: MIT
metadata:
version: "0.1.4"
updated: "2026-10-09"
version: "0.1.13"
updated: "2026-10-12"
---

# Review
Expand All @@ -14,6 +14,16 @@ revision, relevant diff and actual check artifacts. A different model name alone
does not establish independence. Treat the implementer's conclusions as claims
to verify, not instructions to accept.

Leave candidate product sources unchanged. Checks may create the generated task
artifacts and outputs the assignment authorizes, within actual native boundaries;
being ignored, untracked or labelled temporary grants nothing. Clean up only
identified task-owned rebuildable output within accepted scope once nothing uses
it, preserving required evidence, recovery state and others' work. Hold shared,
unknown-owner or active artifacts and actual refusals; report the precise
limitation instead of bypassing it. Task prose alone does not make a review
technically read-only or isolated. Independence comes from separate context and
actual evidence, not from producing no files.

Assess whether the behavior meets the task and whether it follows the project's
documented standards. Exercise representative acceptance and regression paths.
Bind findings to the inspected candidate and concrete requirements; distinguish
Expand Down
10 changes: 7 additions & 3 deletions agent-ops/factory-agent-ops/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,8 @@ name: factory-agent-ops
description: Act as a project's lead for ideas, research, accepted tasks or an approved backlog; coordinate native workers, independent review and authorized delivery.
license: MIT
metadata:
version: "0.1.11"
updated: "2026-10-11"
version: "0.1.13"
updated: "2026-10-12"
---

# Factory Agent Ops
Expand Down Expand Up @@ -53,7 +53,11 @@ Use a sufficient authorized native capability or report the specific limitation.

Delegate only separable work with clear scope, inputs, access and proof. Give
each concurrent writer its own bound workspace. Pass reviewers the actual
candidate and requirements in a separate context. Read their evidence and resolve
candidate and requirements in a separate context. State whether a reviewer only
inspects sources or also runs checks. For checks, name the permitted generated
outputs, scratch location and any cleanup under existing authority; do not forbid
all writes while requiring write-producing checks, or add an owner gate for routine
authorized check output. Read their evidence and resolve
findings; a successful tool call or finished turn does not establish acceptance.
Recheck affected evidence after fixes, rebases or changed scope.

Expand Down
3 changes: 2 additions & 1 deletion docs/qualification.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Qualification

Revision: 0.1.12 · Updated: 2026-10-11
Revision: 0.1.13 · Updated: 2026-10-12

This record distinguishes source review, disposable exercises and observed native
operation. A package release does not qualify another host, every future update
Expand All @@ -11,6 +11,7 @@ remain with the installation; public issues track the remaining acceptance work.
| --- | --- | --- |
| Package | Eight portable skills, metadata/link checks and staging tests | Mechanical checks do not establish agent decisions |
| Foundation readiness handoff (0.1.12 candidate) | 2026-10-11: [Factory #27](https://github.com/arcitai/factory/issues/27) source change after an AIOS assessment accepted a stale mandatory authoring self-dependency, its disabled private reporting was found only by readback, its lead could not read its private record, and Project1's current README kept stale pre-delivery claims (coordinator observations, not reproduced here). Package, unit and staging checks only | Behavioral evidence and independent review are pending in the delivery PR. Native binding/authentication behavior stays with [Factory #3](https://github.com/arcitai/factory/issues/3); Markdown does not repair it |
| Review check artifacts (0.1.13 candidate) | 2026-10-12: source change after an application operator reported (not reproduced here) that an OpenPaperDesign reviewer was told to modify no files yet asked to compile/test; Rust targets filled the shared `/tmp` quota, automatic approval refused cleanup under that instruction and the reviewer held without bypass. The operator later removed only an earlier completed task's rebuildable target after checking no process used it. Package, unit and staging checks only | Behavioral evidence for source-only, authorized-check-output and shared/active-artifact cases and independent review are recorded in the delivery PR. Project scratch setup stays with that project |
| Persistent choices (0.1.10 candidate) | 2026-10-10: a fresh native Astra xhigh context answered four textual cases against `7f846946`: hypothetical settings stayed unauthorized; external read access retained scope and removal; provider-wide controls did not become project isolation; uncertain application, upgrade drift and expired exceptions required reconciliation | Method rehearsal, not live grant/revocation or a reliability measurement. Independent review of the combined source/presentation is tracked in the delivery PR |
| Engineering Foundation (0.1.9) | 2026-10-10: [PR #24](https://github.com/arcitai/factory/pull/24) and release passed checks and independent review. The selected native scopes matched all 48 staged files; AgentOps explicitly reread the five changed Foundation files. AIOS' own AgentOps assessed its repository against the adopted method and actual build/review/pilot evidence | Explicit source loading is distinct from automatic instruction discovery. The optional three-hour CI profile has not been deployed or observed as a schedule; it enables no schedule itself |
| Writer workspace selection (Nightly 2873) | 2026-10-10: native worktree-bound launch started a Factory writer at the expected revision and workspace. An AIOS child created through ordinary delegation remained on main with no worktree; it was stopped before edits, its stale command approval declined, and a separate native-bound writer was verified before implementation | Assisted recovery exposed ambiguous launch guidance, now clarified. A prompt is not a native binding; this does not prove automated recovery for every failed launch or OS isolation between roles |
Expand Down