diff --git a/VERSION b/VERSION index 0e24a92..7ac4e5e 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -0.1.12 +0.1.13 diff --git a/adlc/factory-review/SKILL.md b/adlc/factory-review/SKILL.md index 5088ffb..bfaeefd 100644 --- a/adlc/factory-review/SKILL.md +++ b/adlc/factory-review/SKILL.md @@ -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 @@ -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 diff --git a/agent-ops/factory-agent-ops/SKILL.md b/agent-ops/factory-agent-ops/SKILL.md index 9ef5099..73da501 100644 --- a/agent-ops/factory-agent-ops/SKILL.md +++ b/agent-ops/factory-agent-ops/SKILL.md @@ -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 @@ -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. diff --git a/docs/qualification.md b/docs/qualification.md index fa70faa..e586fc4 100644 --- a/docs/qualification.md +++ b/docs/qualification.md @@ -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 @@ -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 |