@chrono-meta/fh-gate 3.1.2 → 3.1.4

package/.claude-plugin/marketplace.json

@@ -11,19 +11,19 @@
   "plugins": [
     {
       "name": "fh-meta",
-      "version": "3.1.2",
+      "version": "3.1.4",
       "description": "New in 2.2.0: BREAKING (gate): chamber step 6 now reads ACTUAL.md, not BUDGET.md — an in-flight chamber run whose actual cost sits in BUDGET.md blocks until the ACTUAL: line moves to tracks/_chamber/<slug>/ACTUAL.md (the runner prints the path). Why: BUDGET.md's pre-verdict hash IS the ordering witness, and step 6 hard-blocked until that same file changed, so every run that reached COMPLETE necessarily mutated a witnessed artifact and verify returned TAMPERED — the chamber's promotion condition was unsatisfiable by construction, not by strictness. Two roles (immutable witness / post-verdict calibration sink) had collided in one file; each was correct alone, so neither side's code showed the conflict. Also: ko-tech-writer Step 2/4-b scans are now calibration-backed (known-pair fixtures + reproducible command, shipped) — discrimination is proven, 'zero residue' is explicitly NOT; chamber lane suite 12 -> 33 including the runner x witness seam no test covered; chamber_run.sh now teaches the two-commit discipline (gate hashes and verdict hash must land in separate commits/PRs — it previously advised the opposite). New in 2.1.0: BREAKING (gate): `crossfamily: declined` in an Axes 2-3 marker now requires grounds naming a record path that RESOLVES on disk — bare `declined`, and `declined` justified by author judgment, are blocked at commit. Remedy: cite where the operator decision lives (e.g. `.. — operator declined sidecars, per knowledge/shared/rules/operational_adaptation.md`), or use `DEGRADED_PANEL_UNUSED` if a panel was reachable and you chose not to recruit it — which is what author judgment actually is. `declined` was the only enum value with no grounds requirement; a cross-family review then broke the first (vocabulary-grep) fix three ways — self-validating on the value's own token, vacuous keyword passes, and over-blocking real declinations in natural prose — so the check asserts a resolvable record instead of words. Also: standpoint axis gains `tier1b` (a STATIC read of a target repo, executed nothing) plus a decide-in-order procedure, after blind floor-tier sims graded pure cold-reads as `tier2` three rounds running; steel-quench Wave 1's sixth angle (gate-locality) gains the output-template row it never had, so a mandatory angle stops being structurally unreportable; verify-bidirectional gains category 5 (prescriptive doctrine statement); Sister Asset Protocol gains an active-adoption trigger; new resident doctrine — Mechanization Boundary, Local Execution First, Skeleton-not-Muscle, Expedition track, and this package's versioning policy. Hub meta-operations toolkit — 35 skills + 7 agents. New in 2.0.1: harness-doctor cadence hook, portability lint wired into pre-commit, branch_claim.sh claim-count-vs-tree-count warning, louder confidentiality-scan fail-open notice, fh-gate.sh missing-package.json survival, identity ① reclassified 🟢 (cross-harness adapters + relay argument channel). New in 1.4.53: `fh-codex-doctor` (npm bin) — Codex adapter drift scanner; reads the documented M1/M2/M3 skill tier map + skill/agent source and reports codex-native/adapter-required/claude-native/unclassified per unit, wired into `npm test`/`prepublishOnly` (fail-closed on unclassified Claude-native primitives). New in 1.4.49: steel-quench gains Step 0.6 Verdict-Invariance Probe (groundedness axis — a load-bearing judged gate's verdict must track behavior, not rubric phrasing; measured flip-count over cross-family paraphrases; arXiv:2605.06161 Policy Invariance anchor); multi_model_sidecar_strategy §Vendor-native harness (a model is strongest in its own vendor CLI — Claude/CC, GPT/codex, Gemini/Antigravity; a universal router degrades all of them, so it stays an autocomplete/QA sidecar, never orchestration); predelete_check.sh fail-closed rewrite; memory-hygiene A-TMA anchor. New in 1.4.48: phantom-quench + steel-quench gain external frontier anchors (arXiv:2607.02052 package-hallucination; arXiv:2607.02057 prompt-coverage-adequacy); README model-flat claim reframed from a per-release point-curve to structural invariants (operation flattens across tiers; depth tier-order fixed within a generation). New in 1.4.47: onboarding step ① surfaces the Mode D companion-store session-start load in the auto-read salience anchor (previously only in the local binding + rules, so a greeting could skip the load). New in 1.4.46: context-doctor command-output axis (route to rtk/proxy for verbose CLI stdout, complementing .claudeignore; risk-gated to token-scarce envs). New in 1.4.41: context-doctor 2026 trigger vocab (context engineering/rot/collapse) + phantom-citation hardening; hub measurement-integrity-checklist (cross-model measurement pre-flight: display-name pin/reps≥3/discriminating probe). New in 1.4.40: install-wizard queryable-wiki scaffold (INDEX + session-start read + R/W/C ingest). New in 1.4.39: auto-decorrelation (cross-family verifier sidecar recruitment) + video-ingest (capability-routed video ingestion). New in 1.4.x: verify-axis check-class taxonomy (mandatory-pass/measured/judged), no-reinvention Tier-0 inventory, 7-class failure taxonomy, Destructive-Op Gate, Wave-T (Temper), tier-floor governance, Mode D Model Notice, FC consent lane, default-Sonnet guidance. New in 1.3.0: public-surface-audit, field-harvest Mode B auto-trigger, 4-axis gate scope ext. Validated cross-CLI: Claude Code, Codex, Gemini.",
       "source": "./plugins/fh-meta"
     },
     {
       "name": "fh-commons",
-      "version": "3.1.2",
+      "version": "3.1.4",
       "description": "Project-agnostic utility skills — 5 skills (convergence-loop · deliberation · mcp-circuit-breaker · token-budget-gate · ko-tech-writer) + 1 agent (quench-challenger). Domain-independent utilities transplantable into any project.",
       "source": "./plugins/fh-commons"
     },
     {
       "name": "fh-qp",
-      "version": "3.1.2",
+      "version": "3.1.4",
       "description": "QP (Quality Platform) — the generic edition of a field QA harness's Prepare→Automation→Regression loop as an FH plugin: 4 skills (qp router · qp-plan · qp-run · qp-regress) + qp_tools.sh (target-class · adapter-probe · mask · surface-reach · mtm-check · run-verbs, typed exit codes) + a zero-domain-constant profile slot + 29 known-pair lanes. Drives web targets through the session's Playwright MCP and desktop targets through computer-use MCP (mobile deferred); calls a registered qasp typed capability when one exists (strictest-wins) — none is registered today, so the MCP fallback is the first edition. Verdict contract: a MACHINE closure requires a recorded assertion; a failed first step is attributed BLOCKED, not FAIL; surface_reach counts every TC in the denominator. Born as chamber run #18 (EMIT, 2026-09-05).",
       "source": "./plugins/fh-qp"
     }

package/README.ja.md

@@ -7,6 +7,7 @@
   <a href="https://github.com/VoltAgent/awesome-agent-skills#community-skills"><img src="https://img.shields.io/badge/listed_in-awesome--agent--skills-0ea5e9.svg" alt="Listed in awesome-agent-skills"></a>
   <a href="https://github.com/anthropics/claude-code"><img src="https://img.shields.io/badge/Claude_Code-compatible-a855f7.svg" alt="Claude Code compatible — official Claude Code repository"></a>
   <a href="https://chrono-meta.github.io/forge-harness/"><img src="https://img.shields.io/badge/whole_map-interactive-6366f1.svg" alt="FH whole map — interactive diagrams on GitHub Pages"></a>
+  <a href="https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict"><img src="https://img.shields.io/badge/GitHub_Action-marketplace-2088FF.svg" alt="GitHub Actions Marketplace — fh-gate"></a>
   <a href="https://www.npmjs.com/package/@chrono-meta/fh-gate"><img src="https://img.shields.io/npm/v/@chrono-meta/fh-gate.svg?color=cb3837" alt="npm"></a>
   <a href="https://github.com/chrono-meta/homebrew-forge-harness"><img src="https://img.shields.io/badge/homebrew-tap-FBB040.svg" alt="Homebrew tap"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-22c55e.svg" alt="MIT License"></a>
@@ -65,6 +66,8 @@ brew tap chrono-meta/forge-harness && brew install forge-harness   # あるい
     ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 
+[GitHub Actions マーケットプレイス](https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict) に掲載されている。
+
 このステップは `verdict`（PASS · PENDING · BLOCKED · ESCALATE · HARNESS_ERROR · ARG_ERROR ·
 DRY_RUN · UNKNOWN）と `reviewed` を出します。**`reviewed: false` は合格ではありません** —
 バックエンドが最後まで答えなかった場合、dry run、このラッパーが知らない終了コード、そのすべてが
@@ -433,8 +436,9 @@ Claude Code は作業の複雑さでモデルを自動選択しません — こ
 | [`docs/CONTRIBUTING.md`](docs/CONTRIBUTING.md) | スキルとパターンの貢献方法 |
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **同意レーン** — 非識別化した作業セッションを共有; レポが運用者たちにまたがって複利で積み上がる |
 
-> **FH 論文**: v1.0 方法論 · [Zenodo](https://zenodo.org/records/20397566) (DOI
-> 10.5281/zenodo.20397566) · cs.SE companion、掲載済み ·
-> [Zenodo](https://zenodo.org/records/20680081) (DOI 10.5281/zenodo.20680081) · cs.AI companion は
+> **FH 論文**: v1.0.1 方法論 · [Zenodo](https://zenodo.org/records/22542168) (DOI
+> 10.5281/zenodo.22542168) · cs.SE companion v1.2.1、プレプリント公開 ·
+> [Zenodo](https://zenodo.org/records/22635721) (DOI 10.5281/zenodo.22635721) ·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218) (2026-09-07 時点で arXiv は v1) · cs.AI companion は
 > 準備中。これら、独立した収束的研究、そしてそれぞれの但し書き:
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md)。

package/README.ko.md

@@ -7,6 +7,7 @@
   <a href="https://github.com/VoltAgent/awesome-agent-skills#community-skills"><img src="https://img.shields.io/badge/listed_in-awesome--agent--skills-0ea5e9.svg" alt="Listed in awesome-agent-skills"></a>
   <a href="https://github.com/anthropics/claude-code"><img src="https://img.shields.io/badge/Claude_Code-compatible-a855f7.svg" alt="Claude Code compatible — official Claude Code repository"></a>
   <a href="https://chrono-meta.github.io/forge-harness/"><img src="https://img.shields.io/badge/whole_map-interactive-6366f1.svg" alt="FH whole map — interactive diagrams on GitHub Pages"></a>
+  <a href="https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict"><img src="https://img.shields.io/badge/GitHub_Action-marketplace-2088FF.svg" alt="GitHub Actions Marketplace — fh-gate"></a>
   <a href="https://www.npmjs.com/package/@chrono-meta/fh-gate"><img src="https://img.shields.io/npm/v/@chrono-meta/fh-gate.svg?color=cb3837" alt="npm"></a>
   <a href="https://github.com/chrono-meta/homebrew-forge-harness"><img src="https://img.shields.io/badge/homebrew-tap-FBB040.svg" alt="Homebrew tap"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-22c55e.svg" alt="MIT License"></a>
@@ -52,6 +53,8 @@ brew tap chrono-meta/forge-harness && brew install forge-harness   # 또는 이
     ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 
+[GitHub Actions 마켓플레이스](https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict)에 등재돼 있다.
+
 이 스텝은 `verdict`(PASS · PENDING · BLOCKED · ESCALATE · HARNESS_ERROR · ARG_ERROR · DRY_RUN ·
 UNKNOWN)와 `reviewed` 를 내놓습니다. **`reviewed: false` 는 통과가 아닙니다** — 백엔드가 끝내 답을
 주지 않은 경우, dry run, 이 래퍼가 모르는 종료 코드가 전부 여기로 떨어지고, 기본값에서는 전부 스텝을
@@ -421,8 +424,9 @@ Claude Code 는 작업 복잡도로 모델을 자동 선택하지 않습니다.
 | [`docs/CONTRIBUTING.md`](docs/CONTRIBUTING.md) | 스킬과 패턴 기여 방법 |
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **동의 레인** — 비식별화된 작업 세션 공유. 레포가 운영자들에 걸쳐 복리로 쌓임 |
 
-> **FH 논문**: v1.0 방법론 · [Zenodo](https://zenodo.org/records/20397566) (DOI
-> 10.5281/zenodo.20397566) · cs.SE companion, 게재됨 ·
-> [Zenodo](https://zenodo.org/records/20680081) (DOI 10.5281/zenodo.20680081) · cs.AI companion
+> **FH 논문**: v1.0.1 방법론 · [Zenodo](https://zenodo.org/records/22542168) (DOI
+> 10.5281/zenodo.22542168) · cs.SE companion v1.2.1, 프리프린트 공개 ·
+> [Zenodo](https://zenodo.org/records/22635721) (DOI 10.5281/zenodo.22635721) ·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218) (2026-09-07 기준 arXiv 는 v1) · cs.AI companion
 > 준비 중. 이것들과 독립적인 수렴 연구, 그리고 각각의 주의사항:
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md).

package/README.md

@@ -7,6 +7,7 @@
   <a href="https://github.com/VoltAgent/awesome-agent-skills#community-skills"><img src="https://img.shields.io/badge/listed_in-awesome--agent--skills-0ea5e9.svg" alt="Listed in awesome-agent-skills"></a>
   <a href="https://github.com/anthropics/claude-code"><img src="https://img.shields.io/badge/Claude_Code-compatible-a855f7.svg" alt="Claude Code compatible — official Claude Code repository"></a>
   <a href="https://chrono-meta.github.io/forge-harness/"><img src="https://img.shields.io/badge/whole_map-interactive-6366f1.svg" alt="FH whole map — interactive diagrams on GitHub Pages"></a>
+  <a href="https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict"><img src="https://img.shields.io/badge/GitHub_Action-marketplace-2088FF.svg" alt="GitHub Actions Marketplace — fh-gate"></a>
   <a href="https://www.npmjs.com/package/@chrono-meta/fh-gate"><img src="https://img.shields.io/npm/v/@chrono-meta/fh-gate.svg?color=cb3837" alt="npm"></a>
   <a href="https://github.com/chrono-meta/homebrew-forge-harness"><img src="https://img.shields.io/badge/homebrew-tap-FBB040.svg" alt="Homebrew tap"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-22c55e.svg" alt="MIT License"></a>
@@ -54,6 +55,8 @@ brew tap chrono-meta/forge-harness && brew install forge-harness   # or this
     ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 
+Listed on the [GitHub Actions Marketplace](https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict).
+
 The step exposes `verdict` (PASS · PENDING · BLOCKED · ESCALATE · HARNESS_ERROR · ARG_ERROR · DRY_RUN · UNKNOWN)
 and `reviewed`. **`reviewed: false` is not a pass** — a backend that never answered, a dry run, or an exit
 code this wrapper does not know all land there, and all of them fail the step by default. That default is
@@ -412,8 +415,9 @@ and the phrase that triggers it:
 | [`docs/CONTRIBUTING.md`](docs/CONTRIBUTING.md) | How to contribute skills and patterns |
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **Consent lane** — share a de-identified work session; the repo compounds across operators |
 
-> **FH papers**: v1.0 methodology · [Zenodo](https://zenodo.org/records/20397566) (DOI
-> 10.5281/zenodo.20397566) · cs.SE companion, published ·
-> [Zenodo](https://zenodo.org/records/20680081) (DOI 10.5281/zenodo.20680081) · cs.AI companion in
+> **FH papers**: v1.0.1 methodology · [Zenodo](https://zenodo.org/records/22542168) (DOI
+> 10.5281/zenodo.22542168) · cs.SE companion v1.2.1, preprint ·
+> [Zenodo](https://zenodo.org/records/22635721) (DOI 10.5281/zenodo.22635721) ·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218) (arXiv shows v1 as of 2026-09-07) · cs.AI companion in
 > preparation. Those, the independent convergent work, and the caveats on each:
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md).

package/README.zh.md

@@ -7,6 +7,7 @@
   <a href="https://github.com/VoltAgent/awesome-agent-skills#community-skills"><img src="https://img.shields.io/badge/listed_in-awesome--agent--skills-0ea5e9.svg" alt="Listed in awesome-agent-skills"></a>
   <a href="https://github.com/anthropics/claude-code"><img src="https://img.shields.io/badge/Claude_Code-compatible-a855f7.svg" alt="Claude Code compatible — official Claude Code repository"></a>
   <a href="https://chrono-meta.github.io/forge-harness/"><img src="https://img.shields.io/badge/whole_map-interactive-6366f1.svg" alt="FH whole map — interactive diagrams on GitHub Pages"></a>
+  <a href="https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict"><img src="https://img.shields.io/badge/GitHub_Action-marketplace-2088FF.svg" alt="GitHub Actions Marketplace — fh-gate"></a>
   <a href="https://www.npmjs.com/package/@chrono-meta/fh-gate"><img src="https://img.shields.io/npm/v/@chrono-meta/fh-gate.svg?color=cb3837" alt="npm"></a>
   <a href="https://github.com/chrono-meta/homebrew-forge-harness"><img src="https://img.shields.io/badge/homebrew-tap-FBB040.svg" alt="Homebrew tap"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-22c55e.svg" alt="MIT License"></a>
@@ -64,6 +65,8 @@ brew tap chrono-meta/forge-harness && brew install forge-harness   # 或者用
     ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
 ```
 
+已在 [GitHub Actions 应用市场](https://github.com/marketplace/actions/fh-gate-typed-ai-code-review-verdict) 上架。
+
 这个 step 会输出 `verdict`（PASS · PENDING · BLOCKED · ESCALATE · HARNESS_ERROR · ARG_ERROR ·
 DRY_RUN · UNKNOWN）和 `reviewed`。**`reviewed: false` 不是通过** —— 后端始终没有回答、一次 dry
 run、这层封装不认识的退出码，全都落在这里，而且默认全部让这个 step 失败。这个默认值正是重点：
@@ -400,8 +403,9 @@ Claude Code 不会按任务复杂度自动选择模型 —— 这个要你设置
 | [`docs/CONTRIBUTING.md`](docs/CONTRIBUTING.md) | 如何贡献技能与模式 |
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **同意通道** —— 分享一个去标识化的工作会话；仓库在众多操作者之间复利累积 |
 
-> **FH 论文**：v1.0 方法论 · [Zenodo](https://zenodo.org/records/20397566)（DOI
-> 10.5281/zenodo.20397566）· cs.SE companion，已发表 ·
-> [Zenodo](https://zenodo.org/records/20680081)（DOI 10.5281/zenodo.20680081）· cs.AI companion
+> **FH 论文**：v1.0.1 方法论 · [Zenodo](https://zenodo.org/records/22542168)（DOI
+> 10.5281/zenodo.22542168）· cs.SE companion v1.2.1，预印本公开 ·
+> [Zenodo](https://zenodo.org/records/22635721)（DOI 10.5281/zenodo.22635721）·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218)（截至 2026-09-07，arXiv 为 v1）· cs.AI companion
 > 筹备中。这些、独立的收敛性工作，以及每一项的注意事项：
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md)。

package/docs/OUTPUT_EVIDENCE.md

@@ -35,8 +35,8 @@
 
 | Artifact | Reference |
 |---|---|
-| Paper v1.0 — methodology | Zenodo DOI [`10.5281/zenodo.20397566`](https://zenodo.org/records/20397566) — 2-layer design, 6-axis framework, 4-agent orchestration, compounding loop, with empirical evidence. arXiv in review |
-| cs.SE companion — governance-gate methodology | **published** · Zenodo DOI [`10.5281/zenodo.20680081`](https://zenodo.org/records/20680081) (latest v1.1 `10.5281/zenodo.20740038` · CC-BY-4.0) · arXiv **submitted** (cs.SE). The moderation outcome is not tracked in this repo, so treat "submitted" as the last state this page can vouch for, not as current |
+| Paper v1.0.1 — methodology | Zenodo DOI [`10.5281/zenodo.22542168`](https://zenodo.org/records/22542168) (all versions: `10.5281/zenodo.20397565`) — 2-layer design, 6-axis framework, 4-agent orchestration, compounding loop, with empirical evidence. **arXiv: rejected at moderation (2026-09-06)**; v1.0.1 is the corrected version (11 of 17 reference entries in v1.0 did not match the works cited — see the erratum in the record). Do not read the rejection as an assessment of the methodology, and do not read v1.0.1 as re-reviewed: it has not been resubmitted |
+| cs.SE companion — governance-gate methodology | **preprint, publicly posted** · Zenodo DOI [`10.5281/zenodo.22635721`](https://zenodo.org/records/22635721) (v1.2.1; the record's description carries the per-version change notes — v1.2 added the replication section and withdrew two previously reported results; v1.2.1 propagates that withdrawal into the abstract and the conclusion, which v1.2 had left unrevised; all versions `10.5281/zenodo.20680080` · CC-BY-4.0) · [`arXiv:2609.04218`](https://arxiv.org/abs/2609.04218) (cs.SE; submitted 2026-07-01, announced 2026-09). 🟥 **As of 2026-09-07 the arXiv record is still v1**, whose abstract carries the severity-differential sentence that §6.6 of the linked Zenodo record withdraws — open both and compare. **Author-reported, not visible on the public record:** a v2 with the v1.2.1 content was submitted 2026-09-07 and its submission confirmation gives a *scheduled* announcement date of 2026-09-09. 🟥 arXiv is a moderated preprint server; moderation is not peer review, and neither the Zenodo deposit nor the arXiv posting establishes peer review, editorial acceptance, or venue acceptance |
 | cs.AI companion — "Governance Dividend" | in preparation |
 | Package | npm [`@chrono-meta/fh-gate`](https://www.npmjs.com/package/@chrono-meta/fh-gate) — multi-backend governance gate (claude · codex · auto) |
 | Codex-compatible | `docs/codex-compat.md` — methodology layer runs model-agnostic. Marked **beta** there in the *validation-maturity* sense (external validation is still thin), **not** the *scope* sense: partial automation-layer support is the design, not an unfinished state |

package/knowledge/shared/harness-core/fh_ecosystem_positioning.md

@@ -146,4 +146,4 @@ This is the N-fold synergy claim stated precisely. The controlled experiment des
 - `multi_model_sidecar_strategy.md` — orchestrator-swap experiment that generated this audit
 - `README.md §Architecture` — 2-layer design (methodology vs automation)
 - `AGENTS.md` — 6-agent registry (fact-checker added after this audit)
-- FH paper (Zenodo: 10.5281/zenodo.20397566) — harness-as-durable-layer thesis this positioning extends
+- FH paper (Zenodo: 10.5281/zenodo.20397565) — harness-as-durable-layer thesis this positioning extends

package/knowledge/shared/harness-core/fh_integration_contract.md

@@ -344,4 +344,4 @@ The bridge layer (v1.0) will implement these. This contract is the specification
 - `fh_ecosystem_positioning.md` — ecosystem context + synergy map + v2 paper connection
 - `tracks/_meta/` — governance logs written here on each gate run
 - `multi_model_sidecar_strategy.md` — multi-model orchestration (related pattern)
-- FH paper (Zenodo: 10.5281/zenodo.20397566) — harness-as-durable-layer thesis this contract operationalizes
+- FH paper (Zenodo: 10.5281/zenodo.20397565) — harness-as-durable-layer thesis this contract operationalizes

package/knowledge/shared/harness-core/fh_opencode_governance_wrapper.md

@@ -160,4 +160,4 @@ On session end, check `/tmp/fh-pending-governance.txt` and run the governance pa
 - `fh_ecosystem_positioning.md` — ecosystem context, synergy map, v2 paper connection
 - `multi_model_sidecar_strategy.md` — multi-model orchestration (sidecar pattern for adding Gemini/Codex review)
 - `tracks/_meta/fh_opencode_governance_experiment_2026_05_31.md` — full empirical record (local)
-- FH paper (Zenodo: 10.5281/zenodo.20397566) — harness-as-durable-layer thesis
+- FH paper (Zenodo: 10.5281/zenodo.20397565) — harness-as-durable-layer thesis

package/knowledge/shared/harness-core/goal_quench_anthropic_issue.md

@@ -84,7 +84,7 @@ Limitations of the userspace approach (why native support is needed):
 - Stop hook cannot invoke Claude recursively (verification triggers on next session, not immediately)
 - Checkpoint requires manual commit — no structured sub-goal output from Haiku
 
-**Paper reference**: forge-harness: A Meta-Harness Engineering Platform for Terminal-Native Claude Code Workflows. Zenodo DOI: 10.5281/zenodo.20397566. arXiv: [pending number].
+**Paper reference**: forge-harness: A Meta-Harness Engineering Platform for Terminal-Native Claude Code Workflows. Zenodo DOI: 10.5281/zenodo.20397565. arXiv: [pending number].
 
 ---
 

package/knowledge/shared/harness-core/multi_model_sidecar_strategy.md

@@ -778,7 +778,7 @@ Missing any layer = compression risk. (Path conventions adapt per project — se
 
 - `README.md §Architecture — 2-layer design` — sidecar note in Automation layer section
 - `knowledge/shared/harness-core/agents_md_runtime_details.md §Sidecar-routing-and-waiting` — sidecar note distinguishing adapter invocation from agent dispatch
-- FH paper (Zenodo DOI: 10.5281/zenodo.20397566, arXiv: submit/7657304) — harness-as-durable-layer thesis
+- FH paper (Zenodo DOI: 10.5281/zenodo.20397565 — all versions) — harness-as-durable-layer thesis. The arXiv submission `submit/7657304` was rejected at moderation 2026-09-06; cite the Zenodo record, not that ID
 - A sister-harness `sidecar-orchestrator` SKILL.md (2026-06-01) — gh copilot + corporate endpoint + 3-tier fallback + 3-layer persistence
 - arXiv:2605.26302 AgingBench — compression aging defense rationale
 - `hybrid_orchestration_architecture_roadmap.md` — proposed (not-yet-implemented) architecture direction that would generalize this sidecar strategy into a hybrid orchestration engine

package/knowledge/shared/learnings/subagent_invocations_log.yaml

@@ -3537,3 +3537,14 @@
   evidence: "논문 B DRAFT2 — 사례표 `memory/` 인용 13행 → **0**(🟥 내가 센 11 이 아니라 13 이었다: `tracks/**` 도 gitignored 라는 걸 에이전트가 `git ls-files --error-unmatch` + known-pair 로 잡았다) · 「few」 → **4/24** · 내부 모순 2건 자체 적발·수리. qasp PR #270 머지(fe95282), CI 6/6 — 🟥 그중 2건은 그 PR 이 만든 결함이고 거버너가 잡아 고쳤다(사유 문구가 CI 가드의 grep 대상 · 자동 탐색이 음성 컨트롤 무력화)"
   tokens_subagent: 700000
   notes: "🟥 사고 하나 — 에이전트가 DRAFT 1 을 제자리 편집으로 덮었고 회수 불가(파일·스냅샷·git 전부 0). **원인은 내 쪽**이다: 「이전 판 남겨라」를 임무문에 산문으로만 적고 발주 전에 커밋하지 않았다. 메모리 `feedback_commit_the_artifact_before_the_next_round` 신설 + DRAFT2 즉시 커밋으로 적용. 🟥 그리고 사이드카 주장 하나(row 29)를 거버너가 재현 못 해 라운드 3 으로 되돌렸다 — 이 논문이 다루는 주제가 바로 그것이라 «그럴듯한데 원 출처에 없는 것」을 실으면 논문이 자기를 반증한다"
+
+- date: 2026-09-07
+  agent: general-purpose ×2 (opus)
+  purpose: "논문 v1.2 개정(분석 → HTML 수술, 같은 에이전트 재개) · qasp #251 판정 경로 조사"
+  tier: opus
+  outcome: accepted
+  evidence: "논문: 복제 3건을 정확히 캐고 🟥 **v1.1 이 안 실은 가장 무거운 사실을 잡았다** — GT recall 이 세 복제 어디에서도 재계산되지 않았고, 논문의 중심 비교 주장이 거기 걸려 있다. 거버너가 독립 grep + 컨트롤(`recall`·`GT` 각 0회 vs `S-grade` 12 · `Cond` 8)로 재확인. 수술 후 검증 11항 전부 통과, 거버너 재검 7항 + 추가 6항 통과. qasp: 정본 먼저 읽고 «#251 은 버그가 아니라 스펙 개정»을 짚었고, lockstep 계약 사본 ~20곳 · 배치 전량 사망 3곳 · 33.6% 의 출처 부재를 전부 파일:줄로 냈다"
+  tokens_subagent: 520000
+  dispatch_count_measured: 131  # session_close_check ④-e 집계. 위 2 엔트리는 «클래스 통합»이고
+                                # 총 스폰 수는 131 이다 — 「2건」만 보면 과소 계상으로 읽힌다
+  notes: "🟥 거버너가 잡은 오류 1건 — qasp 조사가 `web_regress.py:423` 의 `return \"PASS\"` 를 «레포 유일 fail-open» 으로 지목했는데 **틀렸다**. `_STATUS_MAP` 이 세 값만 만들고 그 밖은 두 진입점에서 raise 하며 SKIPPED 는 앞 분기가 먹으므로 소진적 else 다. 정적 패턴만 보고 **도달 가능성을 안 본** 부류. 그리고 내 계기도 한 번 틀렸다(`endswith(\"pass\")` 가 `not-pass` 를 삼켜 8.3% 오출력) — 같은 얼굴이라 PR 본문에 적었다. 두 에이전트 다 «확인 못 한 것»을 이름으로 나열했고 그게 검수를 값싸게 만들었다"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "3.1.2",
+  "version": "3.1.4",
   "description": "FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.",
   "homepage": "https://github.com/chrono-meta/forge-harness#readme",
   "bugs": {

package/plugins/fh-commons/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "fh-commons",
-  "version": "3.1.2",
+  "version": "3.1.4",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

package/plugins/fh-meta/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "fh-meta",
-  "version": "3.1.2",
+  "version": "3.1.4",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

package/plugins/fh-meta/CHANGELOG.md

@@ -1,5 +1,54 @@
 # forge-harness (fh-meta) Changelog
 
+### [3.1.4] — 2026-09-07 — 논문이 arXiv 에 걸렸고, 「published」는 과대주장이었다
+
+3.1.3 과 **같은 사유**다: 소비자가 받는 문서가 더 이상 참이 아니게 됐다.
+
+    이전   cs.SE companion … **published** · Zenodo 22558450
+    지금   cs.SE companion … **preprint, publicly posted** · Zenodo 22635721
+                            · arXiv:2609.04218 (arXiv shows v1 as of 2026-09-07)
+
+두 가지가 같이 바뀌었다.
+
+**① arXiv 등재.** `submit/7775978` 이 68일 온홀드 끝에 통과해 `arXiv:2609.04218`(cs.SE)이 됐다.
+
+**② 「published」를 뺐다.** cross-family 감사(codex)가 과대주장으로 지목했다 —
+**예치(deposit)와 프리프린트 공개는 «게재»가 아니다.** 심사를 통과한 적이 없다.
+자력 적발 0 이었고, 같은 라운드에서 유사한 과대주장 17건이 함께 지목됐다.
+
+**③ Zenodo v1.2.1.** v1.2 가 §6.6 에서 severity 주장을 철회해 놓고 **초록과 §11 결론에는
+그 주장이 그대로 살아 있었다.** v1.2.1 이 그 둘을 철회 문장으로 바꾸고 recall 에
+단일세션 자격표시를 붙였다. 지금 논문 안에 그 주장을 *주장하는* 자리는 0이다.
+
+동작 무변경 — 실행 코드 diff 0건이라 **patch** 다.
+
+### [3.1.3] — 2026-09-07 — 출하 문서가 「arXiv in review」라고 말하는데 반려됐다
+
+링크 정정이 아니라 **거짓 진술** 때문에 올린다. 3.1.2 를 받은 소비자의
+`docs/OUTPUT_EVIDENCE.md` 가 methodology 논문을 이렇게 말하고 있었다:
+
+    Paper v1.0 — methodology | Zenodo … arXiv in review
+
+**2026-09-06 에 모더레이션에서 반려됐다.** 사유는 방법론이 아니라 인용이었다 —
+17개 참고문헌 중 11개가 실제로 인용한 저작과 맞지 않았다. 그 정정본이 v1.0.1 이다.
+
+바뀐 것:
+
+    docs/OUTPUT_EVIDENCE.md   반려 사실 + v1.0.1 정정본 명시.
+                              「방법론에 대한 평가로 읽지 마라」와
+                              「v1.0.1 을 재심사된 것으로도 읽지 마라」를 함께 적었다
+    README ×4                 v1.0.1 (22542168) · 거버넌스 v1.2 (22558450) 로
+    knowledge/ 인용 5곳       concept DOI (20397565) — 판이 아니라 «그 논문»을
+                              가리키는 자리라 항상 최신으로 해석된다
+    multi_model_sidecar…      죽은 arXiv ID `submit/7657304` 를 죽었다고 명시
+    README ×4                 마켓플레이스 진입 경로(배지 + 본문 링크). 슬러그는
+                              추측 3개가 404 인 것을 먼저 확인하고 실측으로 골랐다
+
+동작 무변경 — `action.yml`·게이트·레인 무접촉이라 **patch** 다.
+
+⚠️ 이 릴리스가 검증하지 못한 것: 배지 «이미지» URL. shields.io 는 존재하지 않는
+경로에도 200 을 주므로 그 확인에는 판별력이 없다. 검증된 것은 링크뿐이다.
+
 ### [3.1.2] — 2026-09-07 — Action 설명이 마켓플레이스 한도를 넘어 게시가 막혔다
 
 운영자가 마켓플레이스 개발자 약관에 동의해 게시 체크박스가 열리자, GitHub 의 리스팅 폼이

package/plugins/fh-qp/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "fh-qp",
-  "version": "3.1.2",
+  "version": "3.1.4",
   "engines": {
     "claudeCode": ">=1.0.0"
   },