@chrono-meta/fh-gate 1.4.82 → 1.4.83

package/.claude-plugin/marketplace.json

@@ -11,13 +11,13 @@
   "plugins": [
     {
       "name": "fh-meta",
-      "version": "1.4.82",
+      "version": "1.4.83",
       "description": "Hub meta-operations toolkit — 35 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": "1.4.82",
+      "version": "1.4.83",
       "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/CLAUDE.md

@@ -728,6 +728,10 @@ it is the **first half of** ⑤. A close-time finding has exactly one landing or
 and there is no remaining moment where appending is the natural move. *Honest scope*: this removes
 the ordering ambiguity, not the reflex; the pre-push gate stays the floor, and on a violation it now
 **names the offending files and prints their last lines** so re-running ⑤ is a delta, not a re-read.
+The check also carries a **⑤-b card-drift probe** (advisory, never blocks): it cross-checks the
+card's *absence claims* against on-disk reality (`session_close_check.sh` ⑤-b block) — surfaced
+here because an implemented-and-lane-tested step that no spec document names is exactly the
+orphan-implementation class the 2026-08-01 reverse-verification pilot flagged (P2-08).
 
 **Mid-session card writes are drafts**: If a task (e.g., a calibration run) internally updates
 the card, that is a draft. The close chain always re-runs ⑤ to capture post-draft activities.

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

@@ -303,7 +303,11 @@ command -v gh >/dev/null 2>&1 && gh copilot --help >/dev/null 2>&1 && echo "tier
 #    model-selectable, so pick a non-Claude model from a Claude host for genuine diversity)
 
 # Tier 2 — native API key (pay-per-use; only if no Tier-1 CLI)
-for k in GEMINI_API_KEY OPENAI_API_KEY ANTHROPIC_API_KEY; do
+#   OpenRouter is a VERIFIED Tier-2 route (2026-08-01: a GPT-family audit leg ran 4 calls to
+#   completion when the codex CLI was quota-exhausted — same model, API-shaped). Discipline when
+#   it binds: record the response's model-echo header PER CALL (server-side proof of which model
+#   answered — slug typos silently reroute, the measured agy failure mode; self-report is not it).
+for k in GEMINI_API_KEY OPENAI_API_KEY ANTHROPIC_API_KEY OPENROUTER_API_KEY; do
   [ -n "${!k:-}" ] && echo "tier2:$k"
 done
 

package/knowledge/shared/learnings/subagent_invocations_log.yaml

@@ -608,3 +608,17 @@
   outcome: accepted
   evidence: "Guard R1: 7 bypass + 3 FP classes, JSON-contract violations 0; 3 findings overlapped challenger = independent convergence; 1 suggestion (start-anchoring) refuted with recorded reason, later PARTIALLY vindicated by live prose FPs — resolved with leading-separator class instead of command-position anchor. qasp R1: HIGH status-enum hole independently converged with governor read; core_override_flag requiredness grounded in contract §105 before acting. R2: 5/5 CLOSED, CONVERGED."
   note: "codex unavailable (~8/6); agy carried the cross-family leg for both FH and qasp reviews, mirroring the 07-31 panel precedent."
+- date: 2026-08-01
+  agent: headless claude -p (scratchpad cwd — context-decorrelated audit leg)
+  task: "qasp reverse-verification Run #1: Protocol #2/#4/#5 audit of FH guard+close-chain slice, 21 black-box TCs executed"
+  mode: headless -p, workspace-confined, FH CLAUDE.md not loaded (decorrelation by cwd)
+  outcome: accepted
+  evidence: "CALIBRATED (KP4 re-derived AND executed via TC-DG-03; known-negative FP 0; self-FP-tagged 1). 10 findings -> governor source-ground: 7 novel-grounded (3 S fixed same-evening 2711e0a), 2 rejected as governor corpus-feeding artifacts (agent itself marked both 미확인 — honest). Dynamic leg 17/21 PASS."
+  note: "First field->meta reverse verification. Rejection cause was the governor's slice construction, not the instrument — lesson registered in run report."
+- date: 2026-08-01
+  agent: fh-meta:challenger (in-session isolated)
+  task: "Axis-2 adversarial pass on spec-sync diff (3 fixes from Run #1)"
+  mode: sync Agent dispatch, read-only, 4 attack angles
+  outcome: accepted
+  evidence: "M0/S1/R3. S = same-class stale phrasing in destructive_pre_gate.sh:63 usage comment ('single command') that the diff itself existed to eliminate — fixed same branch. All 4 angles returned evidence, not assertion (grep :83, 3 suite counter prints, JSON tool, ⑤-b never-FAIL)."
+  note: "Angle ④ surfaced an accepted trade: count-free refs lose lane-deletion detection — mechanical suite-internal floor named as the right home if wanted."

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "1.4.82",
+  "version": "1.4.83",
   "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": "1.4.82",
+  "version": "1.4.83",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

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

@@ -1,6 +1,6 @@
 {
   "name": "fh-meta",
-  "version": "1.4.82",
+  "version": "1.4.83",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

package/scripts/destructive_pre_gate.sh

@@ -60,7 +60,8 @@
 # Usage:
 #   hook:  PreToolUse matcher "Bash" → bash scripts/destructive_pre_gate.sh
 #   test:  printf '%s' "<command>" | bash scripts/destructive_pre_gate.sh --stdin-raw
-# Opt out on a single command with a trailing `# noqa: destructive-op`.
+# Opt out with `# noqa: destructive-op` — exempts the ENTIRE Bash payload (whole-command match,
+# see PRECISION OVER RECALL above), not a single line.
 
 set -u
 

package/templates/settings.PreToolUse.snippet.json

@@ -26,7 +26,7 @@
     "one, keyed by script name.",
     "",
     "Verify after wiring (known pair, both directions):",
-    "  bash scripts/test_pipe_verdict_guard_lanes.sh          # 15 pairs, expect all hold",
+    "  bash scripts/test_pipe_verdict_guard_lanes.sh          # expect: all known pairs hold (count is self-reported by the suite — do not pin it here, it rots)",
     "  printf '%s' '{\"tool_name\":\"Bash\",\"tool_input\":{\"command\":\"g.sh | tail; rc=$?\"}}' \\",
     "    | bash scripts/pipe_verdict_guard.sh                 # expect a PIPE-VERDICT R2 warning",
     "",
@@ -38,9 +38,11 @@
     "counterweight is mechanical. Net-new coverage is the LOCAL destructive ops no git hook sees;",
     "the pre-push hook remains the hard floor for the push-time surface (role deconfliction in the",
     "script header). Advisory by design, same contract as pipe_verdict_guard (additionalContext +",
-    "systemMessage, no permissionDecision); escalate with FH_DESTRUCTIVE_BLOCK=1. Opt out per",
-    "command with `# noqa: destructive-op`.",
-    "  bash scripts/test_destructive_pre_gate_lanes.sh        # 99 pairs, expect all hold",
+    "systemMessage, no permissionDecision); escalate with FH_DESTRUCTIVE_BLOCK=1. Opt out with",
+    "`# noqa: destructive-op` — the opt-out exempts the ENTIRE Bash payload (whole-command match),",
+    "not a single line: a multi-statement payload with a destructive line 1 and a noqa on line 2 is",
+    "fully exempt (accepted advisory-surface residual — see the script header's PRECISION OVER RECALL list).",
+    "  bash scripts/test_destructive_pre_gate_lanes.sh        # expect: all known pairs hold (count self-reported)",
     "",
     "THIRD GUARD, Write matcher — stale_clone_guard.sh (added 2026-08-01, fh_signal_2026-07-31):",
     "advisory when a NEW file is created inside a git clone that is behind its upstream (fetch +",
@@ -48,7 +50,7 @@
     "built on a 46-PR-behind clone and manufactured a duplicate of an upstream lane. found→extend",
     "applies at repo level; this is its mechanical layer. Same advisory contract; fail-open on",
     "every uncertainty (non-repo, no upstream, fetch failure).",
-    "  bash scripts/test_stale_clone_guard_lanes.sh           # 10 pairs, expect all hold"
+    "  bash scripts/test_stale_clone_guard_lanes.sh           # expect: all known pairs hold (count self-reported)"
   ],
   "project_settings_json": {
     "hooks": {