@chrono-meta/fh-gate 1.4.65 → 1.4.67

package/.claude-plugin/marketplace.json

@@ -11,13 +11,13 @@
   "plugins": [
     {
       "name": "fh-meta",
-      "version": "1.4.65",
+      "version": "1.4.67",
       "description": "Hub meta-operations toolkit — 34 skills + 7 agents. 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": "1.4.65",
+      "version": "1.4.67",
       "description": "Project-agnostic utility skills — 4 skills (convergence-loop · deliberation · mcp-circuit-breaker · token-budget-gate) + 1 agent (quench-challenger). Domain-independent utilities transplantable into any project.",
       "source": "./plugins/fh-commons"
     }

package/AGENTS.md

@@ -104,17 +104,22 @@ For complex multi-step tasks, run `/agent-composer` first to plan which agents t
 
 The methodology layer (`tracks/`, `knowledge/`, `SKILL.md` docs) is Codex-compatible beta. Any AI model can follow skill workflows by reading SKILL.md files directly; the automation layer (hooks, plugin-channel agents under `plugins/*/agents/`, `/model`) is Claude Code-native and requires manual adaptation. FH's own agents are auto-loaded via the plugin channel when the plugin is enabled — `.claude/agents/` is the field-project override slot, not where FH ships its agents. Non-Claude runtimes use this `AGENTS.md`, `plugins/*/agents/*.md`, and `scripts/fh-run.sh` to apply the same methodology via adapter.
 
-### Non-Claude runtimes: three things CLAUDE.md holds that you will not auto-load
+### Non-Claude runtimes: four things CLAUDE.md holds that you will not auto-load
 
 `.claude/rules/*.md` with `paths:` frontmatter is a **Claude Code platform feature** — those files are
 auto-loaded into a Claude Code session when it reads a matching file, and **your runtime has no equivalent**.
-So three things that govern behavior are not going to reach you on their own. Read them explicitly:
+So four things that govern behavior are not going to reach you on their own. Read them explicitly:
 
 1. **FH asset changes run a mandatory 4-axis verification chain before the session's first commit.**
    Detail (axis definitions · marker required fields · lightweight exception · substantive carve-out):
    `.claude/rules/fh_4axis_gate.md` — **open it directly**; nothing will load it for you. The commit is
    hard-blocked by `templates/.git-hooks/pre-commit` regardless of runtime, so skipping the read does not
    skip the gate — it just means you meet the block without knowing what it wants.
+   ⚠️ If you run `templates/regression_guard.sh` (Axis 1) yourself, **`exit 0` means PASS *or* SKIP** —
+   SKIP being "no staged file matched the gate's pathspec", which is *not checked*, not *checked and
+   clean*. Read stdout for `REGRESSION_GUARD_RESULT=skip` to tell them apart. Judging by exit code
+   alone lets an unexamined change report as a pass (measured 2026-07-22: that is exactly what the
+   commit hook did until it was fixed).
 2. **Company residency is absolute** (CLAUDE.md §Field-Harness Diagnostic): raw company source, secrets,
    hostnames, internal repo/asset names, stack traces, and unredacted findings **never leave the local
    machine** — not to an external *or same-family* cloud model, not through a browser/API tool, not into a
@@ -132,6 +137,34 @@ So three things that govern behavior are not going to reach you on their own. Re
    for you. Your runtime *can* run these lenses: substitute `Agent(subagent_type=...)` per §M2 above
    (`fh-run`, or `codex exec` reading the agent spec). The lens returns evidence, never the verdict.
 
+4. **General work is in scope here, and the mechanism for serving it is to marshal installed
+   capability.** CLAUDE.md §Intent Marshaling makes this the runtime default. It settles a *category*
+   question only — whether non-harness work belongs in this environment at all. Every ordinary check
+   about a specific request (is it safe, sensible, well-formed, worth doing) is yours and is unaffected.
+
+   The category answer is yes, for a concrete reason: the skill registry, the mapped field harnesses,
+   and the memory store exist **only** in this environment. So when the operator states a work intent in
+   plain language (write this doc, build this wiki page, organize this material — **any work-shaped ask,
+   not only harness building**), the scan below is what tells you whether capability for it is actually
+   present. An empty scan, reported with the scan cited, is a correct answer — see the third bullet.
+
+   Three constraints carry over unchanged to your runtime:
+   - **Enumerate rather than recall.** List the available skills, `LOCAL_SKILL_REGISTRY`, and the mapped
+     project assets. Recall under-reports what is installed, which is why the scan is a listing step.
+   - **Marshaling never upgrades a trust tier.** Run-first autonomy covers **FH-native capability whose
+     steps are per-action reversible**. A non-FH sibling capability stays at its registry `ask-tier`
+     (propose only), and an outward-mutating action (send · post · deploy · delete) keeps its own gate.
+   - **A capability gap is declared by citing the scan result**, not as a bare "nothing fits" — then
+     route at request scale (internal scan → external search → in-session synthesis). *Persist* routes
+     to the New-Skill gate; *install* routes to plugin-recommender's HITL. No new gates.
+
+   **This item exists because the triggering utterance is ordinary work language that names no skill and
+   no agent** — like item 3, no automatic trigger covers it; read it explicitly.
+
+> **Detail**: See `knowledge/shared/harness-core/intent_marshaling_general_work.md` — the 5-step loop,
+> the gate-routing table, the Sonnet-floor boundaries, and the origin defect — **open it directly**
+> before applying the ladder or when a gap appears.
+
 The irreversible-surface gates (Pre-Publish · Destructive-Op) likewise live in CLAUDE.md and fire on
 **intent**, not on a file — read them before any publish, delete, or history-rewrite. `pre-push` enforces
 the git-side destructive surface mechanically for every runtime.

package/CATALOG.md

@@ -8,6 +8,18 @@ AI reads this file first when searching past work. Open individual files for det
 
 <!-- Add entries in reverse date order (newest at top) -->
 
+### 2026-07-22 (2) | forge-harness · qasp · pmh | #weekly-audit, #entrypoint-drift, #gate-fail-open, #union-silent-drop, #instrument-attribution, #npm-release
+**File:** tracks/_audit/weekly_audit_2026-07-22.md · AGENTS.md §Non-Claude runtimes item 4 · templates/regression_guard.sh · (qasp) src/api/ensemble.py · (pmh) AGENTS.md §Orchestration Gates
+Weekly audit (07-15~07-22) plus the three cross-repo fixes it surfaced. **Audit's largest finding was a card claim that was false**: the session card's red-flag "frontier-digest job not running — zero logs, zero output" did not survive a hand check (14/14 launchd fires, 12/14 outputs, that day's digest present at 09:03). The real defect is a 14.3% output-miss whose two instances both die on `Connection closed mid-response`, and whose 07-18 retry+watchdog fix engaged **neither mechanism** on its first failure day — recorded as unfixed, root cause not isolated. Card-vs-reality drift reached the N=3 recurrence threshold, so the prescription is a mechanical probe rather than another habit rule. **Entry-point drift** closed in both harnesses (FH PR #163, field meta-harness PR #25): a runtime-default governor rule had landed only in the Claude-native entry point, invisible to every other runtime. The target-tier blind sim rejected the first port — the *wording*, carried over verbatim, read as coercive to a cold third-party reader and was reproduced 3/3, once escalating to "I would flag this to the repo owner". Rewritten as a scope statement; converged 2/2. **Gate fail-open** (PR #165): Axis 1's pathspec omitted three asset classes the canonical rule declares covered, and the resulting not-checked state rendered as a green PASS; adversarial review then caught the fix's own over-blocking (a one-word prose edit produced a hard block) before it could train `--no-verify`. **Field harness UNION** shipped a silent-drop path: two divergent fence-unwrap implementations meant a response accepted by the single backend was discarded whole by the ensemble — in a component whose entire justification is not discarding findings. Published `@chrono-meta/fh-gate@1.4.66`.
+- Decision: port constraints across entry points, never wording — the audience's trust relationship changes with the location. Reversible surfaces report SKIP distinctly from PASS rather than switching to a blocking exit code. Company-derived doc conflicts resolve toward the operator-approved integration branch, never toward a feature branch's older state.
+- Open: the failed single-vs-UNION detection ratio stays UNCALIBRATED — a demonstrated drop path and the "anchor absorbs the gain" hypothesis produce the same number, and no counter existed to separate them; re-measure with the new instrumentation. Skip-vs-pass distinction is wired into the commit hook only; three prose-level consumers still judge by exit code. Card-drift probe and the retry/watchdog reproduction harness remain unbuilt.
+
+### 2026-07-22 | forge-harness | #intent-marshaling, #doctrine, #purpose-organization, #leader-briefing, #conference, #pre-registration
+**File:** knowledge/shared/harness-core/intent_marshaling_general_work.md · CLAUDE.md §Intent Marshaling · (companion store) leader/TF briefing pair · handoff §5-§7
+Two operator insights forged into doctrine. **Intent Marshaling** (PR #161, mirrored to the field meta-harness as its PR #23): the runtime twin of intent-machinization — a work-shaped request in plain language triggers a mechanical capability scan (trust tiers carried in scan output), a one-line compose proposal, then run-first execution; gap declarable only by citing the scan; no new gates (install/persist/outward actions route to existing ones). Verified by Sonnet known-pair sim (2/2 separated) + codex cross-family R1 4/4-confirmed findings (2 HIGH: non-FH ask-tier auto-run hole, per-action reversibility fail-open) fixed to R2 CONVERGED. **Leader-judgment briefing pair** (companion store, operator-approved): QA-team edition (4 judgment axes, measured/pending boundary, act-by-act glossary from operator definitions) + org-TF edition (domain-agnostic layers as protagonist, field harness as the n=1 evidence case, method-stack 8/8 as the domain-agnostic quantitative anchor) — both persona-audited (SHIP_AFTER_M, all findings applied; the audits caught the docs' own optimism twice, which became a self-evidencing section). Conference talk submitted (title A) with **metric pre-registration** pinned in the handoff (calibration / field / org metric sets + before-baseline warning + freeze-timeline insurance).
+- Decision: marshaling autonomy covers FH-native per-action-reversible work only; non-FH registry hits keep ask-tier; specific initiative rows always outrank the fallback row. Briefing scope split two-audience (QA team vs org TF) rather than one doc.
+- Open: marshaling operational track record starts at zero (manifest prediction pending); AGENTS.md port of the marshaling anchor = deferred drift candidate; handoff-reachability defect (untracked file referenced for remote verification) recorded as signal S-1 with a mechanical-check prescription.
+
 > **Backfill note (2026-07-15):** the 07-12 / 07-13 / 07-14 entries below were reconstructed from git
 > history + the session card's completion log during the 2026-07-15 harness-doctor run, which found that
 > CATALOG had stopped at 07-10 while 30 FH-asset commits landed — i.e. 5 days of work were invisible to

package/CLAUDE.md

@@ -524,6 +524,7 @@ Proposal format: `"I see [X]. Want me to run /[skill] to [one-line description]?
 | "help me write a prompt", "build a prompt", "improve this prompt", "prompt template" | `/meta-prompt-builder` |
 | "/goal", "run this autonomously", "big multi-step task", "orchestrate this goal", or **any heavy autonomous/multi-agent run** (proactive — propose *before* running; it is expensive, so the proposal is mandatory, not the auto-run) | `/goal-quench` (budget gate + quality gate) |
 | "I don't know what to build", "how should I approach this", "organize this for me", "clarify this", "정리해줘" (ambiguous request before dispatch) | `/deep-clarify` |
+| **work-shaped request outside the harness domain** — "이 문서 만들어줘", "위키 페이지 써줘", "이 자료 표로 만들어줘", any general work ask no other row or skill catches (**fallback default** — a more specific row above/below always wins: 리서치→deep-research · ambiguous "정리해줘"→deep-clarify · heavy fleet→goal-quench) | **Intent-Marshaling loop** (§Intent Marshaling — mechanical capability scan → one-line compose proposal → run; gap → capability ladder) |
 | "memory feels bloated", "clean up memory", "memory too large", "memory hygiene" | `/memory-hygiene` |
 | "ready to PR", "about to push", "merge this", "PR 올려줘", FH asset changed in session | 4-axis auto-gate (see above — runs automatically, no proposal needed) |
 | **field verdict/gate/safety/irreversible code changed** in a mapped project (function returning a verdict enum / gate exit code / safety-invariant · publish/delete/history path) — **proactive, before merge** | **Field-Harness Load-Bearing Change Gate** (see above → degrade-lint → cross-family review → converge; same rigor as FH assets, applied to field code) |
@@ -600,6 +601,29 @@ Simple file-lookup agents may omit. Agent dispatch works from any mapped project
 
 ---
 
+## Intent Marshaling — General-Work Serving (runtime default)
+
+FH/PMH is a **purpose organization**, not only a meta-harness: when the leader states a work intent in
+plain language — wiki/document production, research-and-write, organizing, **any work-shaped ask, not
+just harness building** — the session **marshals installed capability** (skills · agents · mapped
+harnesses · memory) into a one-line composition proposal and runs it. "This is a harness hub, not for
+that" is a forbidden deflection — serving general work is identity (the registry + mapped harnesses +
+memory exist only here; a plain chatbot cannot marshal them). Marshal-by-feel is the defect this
+replaces (same shape as pre-#158 lens selection): the capability scan is **mechanical** (skill list ·
+`LOCAL_SKILL_REGISTRY` · mapped assets), never recall — and it **carries trust tiers**: run-first
+autonomy covers **FH-native capability with per-action-reversible steps only**; a non-FH sibling hit
+stays at its registry `ask-tier` (propose-only) and an outward-mutating action (send · post · deploy ·
+delete) keeps its own gate — marshaling never upgrades either. Capability gap (declared only by citing
+the scan result, never a bare "nothing fits") → the goal-quench Step C ladder semantics at request
+scale (internal scan → external search → in-session synthesis; **persist** routes to the New-Skill
+gate, **install** to plugin-recommender's HITL — no new gates).
+
+> **Detail (read before applying the ladder or when a gap appears)**:
+> `knowledge/shared/harness-core/intent_marshaling_general_work.md` — the 5-step loop, gate-routing
+> table, Sonnet-floor boundaries, and the origin defect.
+
+---
+
 ## Cross-Project Skill Bus (Active Throughout Session)
 
 Based on LOCAL_SKILL_REGISTRY (Step 1-c), **propose and connect skills from other projects directly**. Proposal: *"{Project} has `{skill-name}`. Want me to dispatch it via Agent?"*

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

@@ -0,0 +1,75 @@
+# Intent Marshaling — General-Work Serving (runtime twin of intent machinization)
+
+> **Status**: doctrine (judgment-shaped, operator-forged 2026-07-22). Companion:
+> `harness_incubator_doctrine.md` covers **forge time** (`intent → forge → agreement → machinery`);
+> this file covers **run time** — what a mapped, skill-equipped environment does with a plain work
+> request. Floor companion: `sonnet_floor_doctrine.md`.
+
+## 1. Doctrine statement
+
+At forge time a harness machinizes intent into new machinery. At **run time**, an environment with
+installed skills, agents, mapped harnesses, and persistent memory is a **purpose organization**: the
+leader states a work intent in plain language, and the session **marshals installed capability into a
+composition and executes** — without the leader naming skills, agents, or files.
+
+**Scope is general work, not only harness work.** Wiki/document production, research-and-write,
+review, organizing, data shaping — any work-shaped request is in-scope. The environment moat is the
+point: a capability registry + mapped harnesses + memory exist *here*, so a plain chatbot session
+cannot marshal what it does not have. Serving general work is therefore **identity, not a favor** —
+"this is a harness hub, not for wiki work" is a forbidden deflection.
+
+## 2. Why doctrine, not mood (origin defect)
+
+2026-07-21: a session marshaled sim/persona skills onto wiki-polishing work "by feel" and the effect
+was large. That was orchestrator taste — the same failure shape lens selection had before the
+Author-Exposure Table (PR #158: picked right 4/4, but by judgment-luck, not machine). Taste survives
+only on strong tiers and good days; a Sonnet-tier session with the same assets would serve the same
+request thinly and call it done. This doctrine converts the marshal decision from taste into a
+mechanical default that survives at the Sonnet floor.
+
+## 3. The marshaling loop (every step Sonnet-runnable)
+
+| Step | Action | Mechanical form |
+|---|---|---|
+| **1 Intent read** | Restate the request as *deliverable + doneness* in one line. Genuinely ambiguous → the existing `/deep-clarify` route, not guessing. | one sentence, embedded in the compose proposal |
+| **2 Capability scan** | Scan what is actually installed/mapped — never recall from memory: ① in-session skill list (description match) ② `LOCAL_SKILL_REGISTRY` / Cross-Project Skill Bus ③ the target project's mapped harness assets. **The scan carries each hit's trust tier with it** (FH-native · non-FH sibling `ask-tier` · external) — trust is scan output, not a later afterthought. | list/grep, not vibes |
+| **3 Compose & run** | One-line composition proposal ("draft via X, then Y as the quality gate"), then **run-first, ask-last** — for **FH-native / session-installed capability whose actions are reversible**. A **non-FH sibling registry hit keeps its registry trust tier**: `ask-tier` = propose-only, never auto-run (`fh_detail_protocols.md` 1-c — sibling code is an injection surface). **Reversibility is judged per action, not per skill**: an installed skill whose step sends/posts/deploys/deletes outward hits that action's own gate (`mcp_tool_gating.md` ask-tier · the irreversibility gates) — marshaling never upgrades an ask-tier action to autonomous. | the one-liner IS the HITL surface for reversible work |
+| **4 Gap → ladder** | Gap may be declared **only by citing the Step-2 scan result** ("scanned ①②③, nothing covers X") — never a bare "nothing fits"; a gap claim without a named scan is the under-serve degrade direction this doctrine exists to close. Then reuse the goal-quench Phase 1.5 Step C **ladder semantics** (order + trust-gating + degrade direction — NOT its max-mode `fit_score` trigger, which stays goal-quench-local): internal registry scan → external search (`plugin-recommender`) → **in-session synthesis** from existing meta-skills (composition, not persisted) → net-new skill only as last resort. | same ladder order, no new machinery |
+| **5 Exposure check** | Deliverable is material (published · carries external claims · others rely on it) → the Author-Exposure Table (`agent-composer` §Author-Exposure) names the review pass before "done". | existing gate, unchanged |
+
+## 4. Gates — reused, none new
+
+| Surface | Gate |
+|---|---|
+| Scan · compose · run **FH-native** installed capability, **per-action reversible** | **none** — autonomous, one-line notice |
+| Dispatching a **non-FH sibling/registry skill** | its **registry trust tier** — `ask-tier` = propose-only, never auto-run (injection surface) |
+| An action that mutates **outward** (send · post · deploy · delete · payment — even via an installed skill) | that action's own gate (`mcp_tool_gating.md` ask-tier · irreversibility gates) — never converted to autonomous by marshaling |
+| External plugin/skill **install** | `plugin-recommender`'s own install-HITL (environment mutation) |
+| **Persisting** a synthesized skill | New-Skill Pre-Commit Gate + `asset-placement-gate` (ephemeral in-session composition needs neither) |
+| Irreversible surfaces (publish · delete · heavy autonomous fleet) | existing gates unchanged (Pre-Publish · Destructive-Op · the goal-quench proposal row) |
+
+## 5. Boundaries
+
+- **Not a heavy-orchestration auto-runner**: a run that would spawn a large multi-agent fleet still
+  proposes `/goal-quench` first (existing row). Marshaling defaults to the **cheapest composition
+  that serves the intent** — one skill beats three when one suffices.
+- **Sonnet floor**: every loop step is list/grep/one-liner/run — no depth-gated judgment on the
+  critical path. Depth escalation is dispatch (consent-gated), never substrate.
+- **Company residency unchanged** — marshaling never widens what may leave the machine.
+- **Operator-taste default**: tuning targets the operator's convenience (operator, 2026-07-22: "if
+  it's convenient for me, that's sufficient" — FH/PMH distributes *how the operator works well*).
+  Per-user adaptation is the UAP's layer, not this file's.
+- **Honesty**: marshaling quality is bounded by what is actually installed — a thin environment
+  marshals thin. The scan reports what it found; it never inflates the roster.
+
+## Done When (adoption, measured)
+
+- A general work request in a mapped environment produces a one-line composition proposal grounded in
+  an actual capability scan (check class: **measured** — target-tier sim at Sonnet, known-pair: one
+  work-shaped positive must marshal, one trivial/out-of-scope negative must NOT add ceremony).
+- No new gate machinery introduced; the mutation points (install · persist · non-FH dispatch ·
+  outward actions) route to existing gates (check class: **mandatory-pass** — grep this file for gate
+  names, confirm all resolve to pre-existing assets).
+- Trust tiers survive marshaling: no path in this file lets a non-FH `ask-tier` hit or an outward
+  action run without its own gate (check class: **mandatory-pass** — cross-family verified 2026-07-22,
+  codex F1/F2 closed).

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

@@ -106,6 +106,14 @@ If `steel-quench`/`phantom-quench` are unavailable in the routine session, note
 `Axis N: skipped (skill unavailable)` — Axis 1 PASS alone unblocks a *draft* PR (Axes 2–3 are the
 operator's residual at merge review).
 
+> ⚠️ **"Axis 1 PASS" 는 종료코드로 판정하지 마라.** `regression_guard.sh` 의 `exit 0` 은
+> **PASS 와 SKIP 을 둘 다** 뜻한다 — SKIP 은 "게이트 pathspec 에 걸린 파일이 없었다"이지
+> "검사했고 괜찮다"가 아니다. 무인 루틴이 종료코드만 보면 **미검사가 draft PR 을 unblock 한다.**
+> 구분: stdout 에 `REGRESSION_GUARD_RESULT=skip` 이 있으면 SKIP 이다 — 그 경우 Axis 1 은
+> *통과가 아니라 미실행*이므로 Axes 2–3 과 같은 운영자 잔여로 올려라.
+> (2026-07-22 실측: `pre-commit` 이 정확히 이 혼동을 일으켜 AGENTS.md 변경이 `✅ PASS` 를
+> 받고 지나갔다. `pre-commit` 은 배선 완료 · 이 루틴을 포함한 나머지 소비자는 **미배선 잔여**.)
+
 **Skip-visibility at the handoff (load-bearing for honest HITL escalation).** When Axis 2
 (challenger / steel-quench) is skipped, the adversarial check did not run autonomously — it becomes
 the *merger's* responsibility. An intelligent hand-off must make that visible at the hand-off point,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "1.4.65",
+  "version": "1.4.67",
   "description": "FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.",
   "license": "MIT",
   "keywords": [

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

@@ -1,6 +1,6 @@
 {
   "name": "fh-commons",
-  "version": "1.4.65",
+  "version": "1.4.67",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

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

@@ -1,6 +1,6 @@
 {
   "name": "fh-meta",
-  "version": "1.4.65",
+  "version": "1.4.67",
   "engines": {
     "claudeCode": ">=1.0.0"
   },