@chrono-meta/fh-gate 1.4.62 → 1.4.63

package/.claude-plugin/marketplace.json

@@ -11,13 +11,13 @@
   "plugins": [
     {
       "name": "fh-meta",
-      "version": "1.4.62",
+      "version": "1.4.63",
       "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": "1.4.62",
+      "version": "1.4.63",
       "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/knowledge/shared/harness-core/persona_container_schema.md

@@ -16,7 +16,7 @@ scope: meta-harness
 > directive.
 >
 > **Consumer status**: sim-conductor extension **SHIPPED 2026-06-20** (same session as this schema) —
-> Persona Discovery ② now fills these 6 slots instead of an ad-hoc directive; §Scale gained the Crowd
+> Persona Discovery ② now fills these slots (7 as of 2026-07-18 — stance added) instead of an ad-hoc directive; §Scale gained the Crowd
 > tier (16-cap lifted behind the marginal-coverage stop) + cost-tier routing; Step 5 adds the graduate
 > step with the admission test below. The A4 clocked write-off trigger is therefore **resolved** — this
 > doc has a live consumer.
@@ -25,7 +25,7 @@ scope: meta-harness
 > reviewed → which gates fire); this profiles the **persona** (who reviews). TPA's profile *drives*
 > which personas to synthesize — they pair, they do not overlap (zero shared fields).
 
-## The container — 6 slots
+## The container — 7 slots
 
 A synthesized persona is a filled instance of these slots. (Empirically used 2026-06-20 to synthesize
 blind `newcomer` / `red-team` / `vulnerable-user` personas that found a real grounding bug a
@@ -38,8 +38,22 @@ design-aware inline pass missed.)
 | **external grounding** | the real artifact files the persona MUST read + (optional) external-search queries that ground the persona in real data | a persona ungrounded in the artifact hallucinates; cheap bounded grounding keeps it economical |
 | **output protocol** | **reuses sim-conductor Step 1.5 parallax shape** (single source — do not re-spec here; it already defines Strengths / Concerns / Open-questions / Absence-check) | one shape across all personas → cross-persona agreement is meaningful (`[[multi-persona-review]]`) |
 | **cost tier** | which model runs this persona (floor-local · heavy-local · frontier) | the economy lever — see §Multi-LLM tier distribution |
+| **stance (온도)** | delivery temperature the persona speaks with: friendly · neutral · hostile (optional — default neutral) | conscious pressure control: the same cast serves onboarding-warmth and red-team pressure without forking personas; field-harvested from a qasp resident-persona pattern (2026-07-18) |
 | **lifecycle** | synthesized · validated · graduated (see §Lifecycle) | most personas stay ephemeral; only proven ones graduate |
 
+**Stance invariant** (the orthogonality guard of this slot — same shape as CLAUDE.md §Voice/Tone):
+stance is a **delivery layer only** and never moves the evidence bar — a hostile persona reports the
+same M-grade findings a friendly one must, and a friendly persona never withholds one to stay warm.
+If two stances of the same persona disagree on *what is a finding* (not how it is said), the stance
+layer has leaked into judgment and that run is invalid. Dispatchers (sim-conductor and any
+persona-dispatch skill) fill the slot when synthesizing — an omitted stance is **recorded as explicit
+neutral** (so "optional" never means "unfilled": the slot always carries a value the run log can cite);
+graduated personas record which stances they were validated at. **Unmechanized residual** (honest
+scope): leak *detection* has no mechanical path yet — no dispatcher runs the same persona at two
+stances to compare finding-sets, so this invariant is salience-enforced; mechanizing it (a paired-stance
+probe) is deliberately deferred behind the n≥2 rule. (Origin: qasp stance parameter, first meta-level
+formalization here — n=1 field use.)
+
 **Isolation invariant**: a synthesized persona dispatches as an **isolated** agent (no main-session
 context inherited). Isolation is the FH mechanism that keeps a blind reaction honest — a `newcomer`
 that knows the design intent is not a newcomer. (2026-06-20: the blind-container personas found
@@ -138,7 +152,7 @@ point (cost-efficiency > build-and-demolish).
 
 `sim-conductor` is the runner that **fills** these slots instead of injecting an ad-hoc role directive.
 The shipped extension (through the FH 4-axis gate, HITL): sim-conductor's Persona Discovery ② reads this
-schema and fills the 6 slots; §Scale lifts its 3–16 cap behind the marginal-coverage stop (Crowd tier)
+schema and fills the slots (7 as of 2026-07-18); §Scale lifts its 3–16 cap behind the marginal-coverage stop (Crowd tier)
 and assigns `cost tier` per persona for multi-LLM distribution; Step 5 adds the graduate step. Routing
 decided by `[[asset-placement-gate]]` (2026-06-20): **not a new forked skill** (≈60–70% overlap with
 sim-conductor's runner role) — this schema is the net-new asset, sim-conductor is extended to consume it.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "1.4.62",
+  "version": "1.4.63",
   "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": "1.4.62",
+  "version": "1.4.63",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

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

@@ -1,6 +1,6 @@
 {
   "name": "fh-meta",
-  "version": "1.4.62",
+  "version": "1.4.63",
   "engines": {
     "claudeCode": ">=1.0.0"
   },

package/plugins/fh-meta/skills/sim-conductor/SKILL.md

@@ -9,7 +9,7 @@ model-note: session-inherit — Sonnet base is first-class (sonnet_floor_doctrin
 # sim-conductor — Meta-Simulation Automation Orchestrator
 
 > Profiles target → derives personas → dispatches parallel agents → M/S/R triage → commit.
-> Personas are sourced installed-first → **filled from the persona-container schema** (6 slots, not an
+> Personas are sourced installed-first → **filled from the persona-container schema** (7 slots as of 2026-07-18 — stance added, not an
 > ad-hoc directive) → external install. Scale: 3 to 16, extensible to a crowd behind the
 > marginal-coverage stop (§Scale).
 
@@ -99,8 +99,8 @@ Recommendation:
 
 #### Persona Discovery (after profile → before dispatch)
 
-> **Schema**: `knowledge/shared/harness-core/persona_container_schema.md` — the 6-slot persona-definition
-> container. ② below **fills** these slots (lens / internal-logic / external-grounding / output-protocol
+> **Schema**: `knowledge/shared/harness-core/persona_container_schema.md` — the 7-slot persona-definition
+> container. ② below **fills** these slots (lens / internal-logic / external-grounding / output-protocol / stance
 > / cost-tier / lifecycle) instead of injecting a shapeless directive. The container is what makes a
 > synthesized persona reproducible and cost-routable; the old "fallback palette" was undefined.
 
@@ -109,7 +109,7 @@ After profiling, sim-conductor determines the needed perspective types, then map
 ```
 For each needed perspective:
   ① Scan installed plugins + .claude/agents/ → exact match? → use it
-  ② Fill the 6-slot persona container — lens · internal-logic · external-grounding · output-protocol
+  ② Fill the 7-slot persona container — lens · internal-logic · external-grounding · output-protocol · stance
        (= Step 1.5 parallax shape) · cost-tier · lifecycle → a defined, reproducible persona; the filled
        container IS the dispatch prompt (replaces the old ad-hoc "fallback palette" directive). Assign
        the cost-tier slot per §Scale cost-tier routing. [Schema: persona_container_schema.md]
@@ -123,8 +123,8 @@ Persona Discovery output:
 
 ```
 Persona Map:
-  beginner       → [installed agent: beginner] OR [filled 6-slot container]
-  challenger     → [installed agent: challenger] OR [filled 6-slot container]
+  beginner       → [installed agent: beginner] OR [filled 7-slot container]
+  challenger     → [installed agent: challenger] OR [filled 7-slot container]
   [profile-specific role] → ⚠️ GAP — plugin-recommender recommends: [X] (install? y/n)
 ```
 
@@ -213,7 +213,7 @@ sim-conductor does **not** run a fixed persona set. It derives needed perspectiv
 
 ```
 ① Installed first — scan installed plugins + .claude/agents/ for a matching persona/agent
-② Container fill — fill the 6-slot persona container for the standpoint; the filled container IS the
+② Container fill — fill the 7-slot persona container for the standpoint; the filled container IS the
      dispatch prompt into a general-purpose Agent (Path B — replaces the old ad-hoc role directive)
 ③ External fetch — chain to /plugin-recommender when ①② insufficient for high-stakes tasks
 ```
@@ -231,7 +231,7 @@ FH ships a coherent **user-mastery spectrum** as real, reusable agents (not prom
 
 > **Lineage**: `beginner` / `main-player` / `expert` are the FH-native frontier successors to the field deep-insight `user` group (newcomer / power-user) — re-derived to FH grade with embedded methodology + Done-When, not name-copied. `challenger` is the advanced form of the field `devil-advocate`. The former standalone skeptic standpoint is folded into `challenger` U1.
 
-**Ad-hoc roles** (② tier — container fill): when the profile demands a standpoint with no shipped agent (e.g. "security auditor", "non-native reader"), fill the 6-slot persona container for that standpoint — the filled container is the dispatch prompt. Prefer ① shipped agents; use ② only for genuinely task-specific one-offs.
+**Ad-hoc roles** (② tier — container fill): when the profile demands a standpoint with no shipped agent (e.g. "security auditor", "non-native reader"), fill the 7-slot persona container for that standpoint — the filled container is the dispatch prompt. Prefer ① shipped agents; use ② only for genuinely task-specific one-offs.
 
 #### Scale
 
@@ -329,7 +329,7 @@ Persona composition adapts to `artifact_type` from Step 0.3 profile:
 | Prompt / config | `beginner` | challenger | Interpretation errors, implicit assumptions |
 | Auth / security-sensitive | challenger + Security-auditor† | `main-player` (Heavy) | Attack surface, privilege escalation |
 
-† Security-auditor = ② tier — the 6-slot persona container filled for a security-auditor standpoint.
+† Security-auditor = ② tier — the 7-slot persona container filled for a security-auditor standpoint.
 
 All personas run in parallel. Findings = M/S/R → M-tier items fixed immediately.