@chrono-meta/fh-gate 1.4.32 → 1.4.34

package/CLAUDE.md

@@ -506,7 +506,13 @@ Closing phrase detected ("wrap up", "done", "good work", "end session", etc.)
   → ④ Memory hygiene — update stale entries + record new session findings
   → ④-b npm freshness — if any npm-shipped asset changed this session (the `package.json` `files[]`
        surface: skills · agents · README · AGENTS.md · CLAUDE.md · CHEATSHEET), **propose an npm
-       republish**: version bump + Pre-Publish Surface Gate (`/public-surface-audit` + `/marketplace-gate`
+       republish**: version bump — and the **same bump MUST propagate in lockstep to every
+       `.claude-plugin/plugin.json` + `.claude-plugin/marketplace.json` version** (single-source =
+       `package.json`). The Codex plugin loader keys its cache path on the *plugin.json* version
+       (`~/.codex/plugins/cache/forge-harness/{plugin}/{version}/`), so a frozen plugin.json serves
+       **stale cached skills to Codex/AGENTS.md users** even after content ships (this exact 3-way
+       drift — fh-meta 1.4.1/1.4.11 vs npm 1.4.32 — was found + fixed 2026-06-17). Then Pre-Publish
+       Surface Gate (`/public-surface-audit` + `/marketplace-gate`
        Check 5) + `npm publish` + **`git tag vX.Y.Z` on the bump commit + `git push origin vX.Y.Z`**
        (tag at publish time, in lockstep with the version — keeps git tags aligned with npmjs.com so
        Releases/Tags never drift). The npm-served README and shipped skills/agents freeze at publish

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "1.4.32",
+  "version": "1.4.34",
   "description": "FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.",
   "license": "MIT",
   "keywords": [

package/plugins/fh-meta/skills/contention-layer/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: contention-layer
-description: When two skills or agents produce conflicting verdicts on the same output, reads the conflict as a signal rather than an error and harvests new skill candidates. Routes skills born from contention to fh-meta if they are meta-layer, to commons plugin if project-agnostic, or to field harvest if domain-specific. Triggered by "two skills conflict", "they produce different conclusions", "contention-layer", "contention harvest".
+description: When two skills, agents, or independent research tracks produce conflicting verdicts on the same output, reads the conflict as a signal rather than an error and harvests new skill candidates or insight deltas. Also accepts a Dual-Track Grounding conflict — an open-frontier research track vs an internally-grounded recall track disagreeing — as a research-layer partial analogue of Non-Model Ground (the grounded track is a time-decorrelated anchor, not a non-model one). Routes skills born from contention to fh-meta if they are meta-layer, to commons plugin if project-agnostic, or to field harvest if domain-specific. Triggered by "two skills conflict", "they produce different conclusions", "contention-layer", "contention harvest", "open vs grounded contradiction", "research tracks disagree".
 user-invocable: true
 allowed-tools: ["Read", "Bash", "Grep", "Write"]
 model: sonnet
@@ -20,16 +20,21 @@ When two skills conflict, **harvest the signal** instead of discarding one. Find
 /contention-layer --skills A B       # specify two skills for contention analysis
 ```
 
-Phrase triggers: "two skills conflict" · "weird when used together" · "they produce different conclusions" · "contention harvest" · "contention"
+Phrase triggers: "two skills conflict" · "weird when used together" · "they produce different conclusions" · "contention harvest" · "contention" · "open vs grounded contradiction" · "research tracks disagree" · "dual-track grounding **+ conflict/disagree/contradict**" (the phrase "dual-track grounding" alone collides with `phantom-quench` on the word "grounding" — measured Step-0.5 probe #3, 2026-06-17; it fires this skill only when a conflict word co-occurs)
+
+```
+/contention-layer --tracks open=<deep-research result> grounded=<memory/CATALOG recall>   # Dual-Track Grounding
+```
 
 ## Step 1. Collect Conflict Points
 
-Record clearly which skills conflicted on which output, and in which direction.
+Record clearly which sources conflicted on which output, and in which direction. The conflicting
+**sources** may be two skills/agents, or two independent **research tracks** (Dual-Track Grounding).
 
 ```
-Conflicting skill A: {skill name} — verdict: {conclusion}
-Conflicting skill B: {skill name} — verdict: {conclusion}
-Conflicting output: {TC / diagnostic report / design document / ...}
+Conflicting source A: {skill name / "open-frontier research"} — verdict: {conclusion}
+Conflicting source B: {skill name / "internally-grounded recall"} — verdict: {conclusion}
+Conflicting output: {TC / diagnostic report / design document / a factual claim / ...}
 Conflict point: {which item, by which criteria difference}
 ```
 
@@ -38,6 +43,36 @@ Conflict point: {which item, by which criteria difference}
 - `Scope conflict`: A includes, B excludes a certain domain
 - `Order conflict`: Same goal approached with different preconditions
 - `Philosophy conflict`: The measurement purpose itself differs (e.g., risk reduction vs coverage maximization)
+- `Track conflict` (Dual-Track Grounding): The same claim is asserted by an **open-frontier** track
+  (deep-research / WebSearch over external sources) and contradicted — or unsupported — by an
+  **internally-grounded** track (memory / CATALOG / past-session recall). The disagreement is the signal.
+
+### Step 1-b. Dual-Track Grounding — Non-Model Ground at the research layer
+
+When the input is two research tracks rather than two skills, the contention IS the mechanism: two
+**time-decorrelated** anchors disagreeing exposes the agreement-bias gap that judge-only synthesis
+hides (a single track, however strong, can be confidently wrong with nothing to contradict it). This is
+a research-layer **partial analogue of Non-Model Ground** (`[[fh_propagation_nonmodel_ground]]`) — the
+grounded track is a **time-decorrelated, provenance-bearing** anchor (written in a prior session against
+recorded sources, so the present session's agreement-bias cannot silently overwrite it). It is **not** a
+true non-model anchor: memory/CATALOG are model-written, so the independence is temporal + provenance,
+not lineage. The honest bias-reduction is that contradicting a provenance-bearing past claim **forces an
+explicit source check** (the challenger-verify pairing below) rather than a silent overwrite.
+
+```
+Open track (frontier):    deep-research / WebSearch — what the external world currently asserts
+Grounded track (internal): memory + CATALOG + past-session recall — what we already established
+  → AGREE      : low signal (corroboration) — log confidence, no harvest
+  → DISAGREE   : HIGH signal — the open track may be newer (our claim is stale → memory-hygiene),
+                 OR our grounded claim is right and the frontier is noise (→ a publishable delta).
+                 Direction is a judged call; pair it with challenger-verify-before-act (source-verify
+                 BEFORE rewriting either side — never let recency alone win) and route to harvest.
+  → UNSUPPORTED: the open track asserts what the grounded track has no record of, and back-trace
+                 (phantom-quench) finds no source → treat as Phantom, not as a new fact.
+```
+
+Dispatch shape: the two tracks run as independent calls (deep-research ∥ grounded recall — agent-composer
+can parallelize), then their outputs enter Step 2 as source A / source B. The harvest gate below is unchanged.
 
 ## Step 2. Contention Essence — Harvest Gate
 
@@ -78,6 +113,13 @@ Routing conclusion:
 
 After confirming routing path, auto-generate a new skill SKILL.md skeleton.
 
+> **Reuse — need-driven scaffold**: this skeleton is also the template for Full-Harness Mode's
+> field-asset scaffold (`auto_project_mapping.md §6`). There the entry is not a conflict but a
+> **skill-worthy recurring pattern** (3+ reps · `#skill-candidate` · `field-harvest`); set
+> `origin: field-scaffold` and replace `contention-parents` with the source pattern pointer. An
+> **agent** variant emits `.claude/agents/{name}.md` (`name`/`description`/`tools` + self-contained
+> prompt) instead of this SKILL.md frontmatter. The field team fills domain content; FH only scaffolds.
+
 ```markdown
 ---
 name: {slug}
@@ -106,13 +148,14 @@ After generating skeleton: **"I will place this draft at {path}. Shall I proceed
 
 ```
 [Contention Harvest Report]
-Conflicting skills: {A} vs {B}
-Conflict type: {Criteria / Scope / Order / Philosophy}
+Conflicting sources: {A} vs {B}
+Conflict type: {Criteria / Scope / Order / Philosophy / Track}
 Harvest Gate: Pass / Fail
   └ Reason: {1 line}
 New skill candidate: {name or none}
 Routing path: {fh-meta / commons / field / n/a}
-Next action: {generate draft / exclude / recommend improving existing skill}
+Track-conflict resolution: {memory-hygiene / publishable-delta / phantom / n/a}   # only for Track conflicts (Step 1-b)
+Next action: {generate draft / exclude / recommend improving existing skill / route track-conflict terminal}
 ```
 
 ## Done When
@@ -122,6 +165,9 @@ All steps 1–4 completed
 + [Contention Harvest Report] output (Harvest Gate Pass/Fail stated)
 + If new skill candidate exists: SKILL.md skeleton generated + user confirmation gate complete
 + If no new skill candidate: "Exclude / recommend improving existing skill" stated and exit
++ If Track conflict (Step 1-b): terminal stated — memory-hygiene (stale grounded claim) OR
+  publishable-delta (frontier was noise, our claim holds) OR phantom-quench (unsupported frontier
+  assertion). A track conflict resolving to a terminal is NOT an "exclude" — it is a routed outcome.
 ```
 
 Verdict: PASS (Harvest Gate Pass — new skill skeleton generated or no candidates confirmed) | CONDITIONAL_PASS (candidates found, user confirmation pending) | FAIL (Harvest Gate Fail — collision unresolvable, no new skill justified) | ESCALATE (role boundary ambiguous, requires human judgment)

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

@@ -40,6 +40,34 @@ Check current cwd harness file structure and determine if FH environment (tracks
 | `.claudeignore` | S-tier — context-doctor execution recommended |
 | `.claude/` directory | M-tier (when rule files exist) |
 
+### Step 2-E. L1-E — ETCLOVG Layer Coverage *(functional-layer lens — orthogonal to the file-presence table above)*
+
+A harness is not only files; it is **seven functional layers** (ETCLOVG — arXiv:2606.06324, a component
+taxonomy *orthogonal* to FH's 6-axis process model; cross-audit
+`tracks/_audit/session_2026_06_19_harnessfix-etclovg-cross-audit.md`). FH adopts only the **taxonomy as a
+coverage lens** — not the paper's scoring model. A **coverage checklist, not a mandate**: not every
+harness needs all seven (a read-only doc harness needs no Execution or Governance). For each layer ask
+"is there an asset covering it?"; surface gaps, let the human judge if each is real for *this* harness.
+
+| Layer | Covers | Typical FH asset | If the gap is judged real → priority hint |
+|---|---|---|---|
+| **E** Execution | isolated/reproducible env, bounded autonomy | Agent-dispatch isolation · goal-quench budget | advisory |
+| **T** Tooling | tool discovery / selection / gating | mcp_tool_gating · plugin-recommender | advisory |
+| **C** Context | what the model sees: card, memory, retrieval | session card · CATALOG · context-doctor | advisory |
+| **L** Lifecycle | loops, retries, orchestration, termination | agent-composer · goal-quench | advisory |
+| **O** Observability | traces / logs / cost to diagnose failures | subagent_invocations_log · audit logs · activity log | advisory |
+| **V** Verification | readiness · intermediate · final · regression checks | 4-axis gate (steel/phantom/regression_guard) | higher-stakes |
+| **G** Governance | permissions · approvals · audit trails | HITL gates · public-surface gate | higher-stakes |
+
+**Relationship to the Harness-Defect Taxonomy (below)**: ETCLOVG = *component coverage* (is the layer
+present?); the Defect Taxonomy = *failure modes* (is a present layer degrading?). Orthogonal — coverage vs health.
+
+**Check class**: judged (advisory) — the presence test is mechanical, but "is this gap real for this
+harness's purpose?" is a judged call, **paired** with the human review at Step 7's M-tier gate. **Never
+auto-tier a missing layer into the M/S/R report** — the priority column is a *hint only if a human
+confirms the gap*, never a verdict the report emits on its own; surface each gap tagged "(human-confirm)".
+(FH's own weak layer is **Observability** — retrospective audit only, no runtime layer; named in the cross-audit.)
+
 ### Step 3. L2 — Complexity Diagnosis
 
 | Check | Verdict |
@@ -184,6 +212,11 @@ coverage (laziness) · judged-pairing rule (bias) · pre-compaction completion l
 ### 🟧 S-tier (Strongly Recommended)
 ### 🟩 R-tier (Recommended)
 
+---
+## ETCLOVG Layer Coverage (L1-E)
+- Covered: [layers with an asset, e.g. E·T·C·L·V·G]
+- Gaps (surfaced, never auto-tiered — each "(human-confirm)"): [e.g. "O Observability (human-confirm) — retrospective audit only, no runtime layer"] or "full coverage"
+
 ---
 ## L5 Pattern Analysis
 - Activity (L5-A): [list]
@@ -195,7 +228,7 @@ coverage (laziness) · judged-pairing rule (bias) · pre-compaction completion l
 - HIGH (spec-only — missing Done When): [list or "none"]
 - LOW (language patterns): [file: L{N}: "{text}" → {suggestion}]
 
-Diagnostic scope: L1~L3 [· L4 · L5 (FH only)] [· --lint]
+Diagnostic scope: L1 (+L1-E ETCLOVG coverage) ~L3 [· L4 · L5 (FH only)] [· --lint]
 ```
 
 M-tier 0 → output "Structure healthy. Maintaining simplification trend."
@@ -255,6 +288,7 @@ Verdict: ✅ CONSISTENT · 🟧 INCONSISTENT (fix before push) · 🟩 REVIEW (i
 | Stage | Completion |
 |---|---|
 | Step 7 M/S/R prescription report output | ✅ Diagnosis complete |
+| Step 2-E ETCLOVG coverage line in report (covered layers + gaps, or "full coverage") | ✅ Layer-coverage lens applied |
 | M-tier 0 + "Structure healthy" output | ✅ Diagnosis complete (no prescription needed) |
 | Step 8 weekly_audit section proposed | ✅ Integration proposal complete |
 | Step 9 Eval-First verdict output (when requested) | ✅ Promotion verdict complete |