@chrono-meta/fh-gate 1.4.66 → 1.4.68

package/.claude-plugin/marketplace.json

@@ -11,13 +11,13 @@
   "plugins": [
     {
       "name": "fh-meta",
-      "version": "1.4.66",
+      "version": "1.4.68",
       "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": "1.4.66",
+      "version": "1.4.68",
       "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

@@ -115,6 +115,13 @@ So four things that govern behavior are not going to reach you on their own. Rea
    `.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*. Prefer the typed file channel — set `REGRESSION_GUARD_RESULT_FILE=<path>` and read
+   `result=pass|review|block|skip|error` from that file (stdout's `REGRESSION_GUARD_RESULT=` line is
+   the no-env fallback). 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

package/CATALOG.md

@@ -8,6 +8,12 @@ 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).

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

@@ -106,6 +106,16 @@ 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: `REGRESSION_GUARD_RESULT_FILE=<path>` 를 설정하고 그 파일의 `result=` 를 읽어라 —
+> typed 채널이 정본이고 stdout `REGRESSION_GUARD_RESULT=` 줄은 env 를 못 쓸 때 폴백이다.
+> `result=skip` 이면 SKIP — 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": "1.4.66",
+  "version": "1.4.68",
   "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": "1.4.66",
+  "version": "1.4.68",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

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

@@ -1,6 +1,6 @@
 {
   "name": "fh-meta",
-  "version": "1.4.66",
+  "version": "1.4.68",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

package/plugins/fh-meta/skills/harness-doctor/SKILL.md

@@ -115,7 +115,6 @@ size instrument* is read. The footprint rows below apply to **both** scopes and
 | **Pointer-illusion**: a CLAUDE.md "detail/detailed procedure" pointer whose target is itself an always-loaded `.claude/rules/*.md` | S-tier — the split saves zero context (rules/ auto-loads regardless); move the target out of auto-load, keep the pointer |
 | weekly_audit 14~30 days elapsed | S-tier |
 | weekly_audit 30+ days elapsed | M-tier |
-| `tracks/_meta/*.md` **reference assets** (excluding dated chronological records — `fh_completed_*` · `fh_signal_*` · `frontier_digest_*` · `session_*` · `weekly_audit_*` · `*_log_*`, whose date lives in the filename by design) missing **both** a role/type tag and a version/date stamp | R-tier — taxonomy gap, not urgent. ⚠️ **Measured FP rate before you act on this**: run against FH itself 2026-07-21 it flagged **99/161 (61%)** un-narrowed and **19/26 (73%)** after narrowing — a row that flags most of a directory is noise, not signal. ⚠️ **No consumer**: grep found **no skill that reads `role`/`type` from these files**. Until one exists this is taxonomy for taxonomy's sake — treat as an inventory observation, never escalate |
 
 **Per-unit ≠ aggregate — do not slide between them.** "Every section earns its scope" (the per-unit
 doctrine test) and "the always-loaded total is affordable" (the budget test) are **different questions, and
@@ -230,51 +229,11 @@ FAIL, the safe direction); and the scope test reads directory *existence*, so th
 field→meta (acceptable: the operator names the target, and the footprint rows apply to **both** scopes
 regardless — but it does skip the field-only line rows).
 
-**Context-File Taxonomy check** (mechanical grep, R-tier only — a coverage lens, not a mandate): L1 (Step 2)
-checks `CLAUDE.md` / `.claudeignore` / `.claude/` existence, but nothing checks `tracks/_meta/*.md` context-file
-existence or taxonomy — this adds both. Note: `tpa_schema.md` classifies this file class (`session_card`) as
-**low** risk / "ephemeral state, low blast radius" — most `tracks/_meta/*.md` files are untagged by design, and
-that is expected, not a defect. This check surfaces untagged files for optional triage on the subset that
-function as durable references (e.g. `reference_next_session_starter.md`); it is not a mandate that every file
-in the directory carry a tag.
-
-Scan for two markers per file — a role/type tag (`role:` or `type:` in frontmatter, or a leading `# Role:`
-line) and a version/date stamp (a `YYYY-MM-DD` date or a `version:` frontmatter key, either in the first 10
-lines). A file missing either marker is untagged — report the file list and count; do not escalate past R
-without a human judging whether the specific file's staleness is actually a problem.
-
-```bash
-# find | while, not a glob — same reason as the always-loaded footprint scan above: an unmatched
-# glob aborts under zsh, and a silent zero-match run must still report, not disappear.
-TARGET="${1:?pass the target root explicitly — cwd is not the target}"
-total=0; untagged=0
-while IFS= read -r f; do
-  [ -n "$f" ] || continue
-  total=$((total + 1))
-  # 연대기 기록물은 파일명에 날짜가 있는 것이 설계다 — taxonomy 대상이 아니다(FP 원인의 78/99)
-  case "$(basename "$f")" in fh_completed_*|fh_signal_*|frontier_digest_*|session_*|weekly_audit_*|*_log_*) continue ;; esac
-  grep -qE '^(role|type):|^# ?Role:' "$f" && tag=yes || tag=no
-  head -10 "$f" | grep -qE '[0-9]{4}-[0-9]{2}-[0-9]{2}|^version:' && stamp=yes || stamp=no
-  if [ "$tag" = no ] || [ "$stamp" = no ]; then
-    untagged=$((untagged + 1))
-    echo "UNTAGGED: $f (role-tag=$tag version-stamp=$stamp)"
-  fi
-done < <(find "$TARGET/tracks/_meta" -maxdepth 1 -name '*.md' 2>/dev/null)
-echo "context-file-taxonomy: $untagged untagged of $total files"
-```
-
-**Named residuals of this scan**: `head -10` can miss a stamp in unusually long frontmatter; `^type:` is not
-fence-scoped, so a stray body line starting `type:` outside frontmatter false-positives `tag=yes` — both push
-toward under-reporting, not over-reporting.
-
-Origin (2026-07-20, frontier-auto): surfaced via [Frontier Digest 2026-07-14](https://github.com/chrono-meta/forge-harness/issues/102#issuecomment-4964058520),
-which described a durable-context-file pattern (role-tagged, versioned files shared across 50+ specialized
-agents) citing `aimultiple.com/llm-orchestration` as its source. A `/phantom-quench` pass on 2026-07-20 found
-that page's retrievable content does not actually discuss this pattern — the digest's citation is mis-attributed
-and no verified primary source has been located. The qualitative taxonomy idea (role/version tagging on context
-files) is adopted here on the digest's description alone and is `SPECULATIVE` per H1/H1-b until a verified
-primary source is found; the "40% fewer tool calls" figure the digest also reported is not cited anywhere in
-this check for the same reason.
+<!-- Context-File Taxonomy check removed 2026-07-22/23 (#153 → weekly-audit #6 decision): consumer
+     re-measure = 0 skills read role:/type: from these files; measured FP 99/161 (61%) un-narrowed,
+     19/26 (73%) after narrowing; origin citation was mis-attributed (SPECULATIVE, no primary source).
+     Decorative unit per doctrine — FP figures preserved in the removal commit message as the
+     regression anchor. Re-adding requires a named consumer first. -->
 
 ### Step 3-L. Language Lint (`--lint` mode only)
 
@@ -466,9 +425,13 @@ Verifies that prescription application didn't strip operational content. Run aft
 | F6 Line reduction ≥30% | S |
 | F7 Bash block syntax (bash -n parse) | M if net increase in bad blocks |
 
-Verdict: ✅ PASS (0M 0S) · ⚠️ REVIEW (0M 1+S) · ❌ BLOCK (1+M).
+Verdict: ✅ PASS (0M 0S) · ⚠️ REVIEW (0M 1+S) · ❌ BLOCK (1+M) · ⏭️ SKIP (검사 대상 0 — **PASS 가 아니다**).
 
 Implementation: `bash templates/regression_guard.sh` (compare vs main) or `bash templates/regression_guard.sh BASE HEAD`.
+**Verdict 는 종료코드가 아니라 typed 채널로 읽어라** — `exit 0` 은 pass 와 skip 둘 다다(2026-07-23):
+`REGRESSION_GUARD_RESULT_FILE=/tmp/rg.$$ bash templates/regression_guard.sh …` 후 파일의
+`result=pass|review|block|skip` 를 판정에 쓴다. `skip` = 미검사 — PASS 로 보고하지 말고 "Axis 1
+해당 없음(대상 파일 0)" 으로 보고한다.
 
 > **Detail**: See `SKILL_detail.md §Step-1-3` — bash scripts for Steps 1~6 (L1~L4 diagnostics) — read when running the diagnostic commands.
 

package/plugins/fh-meta/skills/hub-cc-pr-reviewer/SKILL.md

@@ -120,6 +120,11 @@ All 5 Steps completed
 ```
 
 **→ Mandatory when PR contains SKILL.md / rules / templates changes: `bash templates/regression_guard.sh`** — run Axis 1 (backward check) before merge recommendation is issued. If regression_guard exits with M-tier block, merge recommendation must change to ❌ regardless of other checks.
+**Read the verdict from the typed channel, not the exit code** — `exit 0` means pass **or** skip
+(not-checked). Run with `REGRESSION_GUARD_RESULT_FILE=/tmp/rg.$$` and read `result=` from that file:
+`skip` means Axis 1 **did not examine** this PR (no matching file) — record it as "Axis 1 N/A", never
+as a green check. A merge recommendation that cites an unexamined Axis 1 as PASS is the 2026-07-22
+fail-open class.
 
 ## References