@nexus-cortex/cli 4.124.42 → 4.124.43

package/.env.defaults

@@ -1025,6 +1025,10 @@ CORTEX_ENDTURN_GATE=true
 # [LEDGER 2026-10-02 @4.124.42] wording fix after review: instruction limited to continuous objectives (never pass/fail or test counts); reminder adds 'if the task's required checks are not yet passing, this is not a stop signal — keep fixing them' (a flat test-count series would otherwise have pushed an early finish).
 # noisy-line parsing, firing cap, lever-off path, STATUS segment; plateauStop.integration.test.ts: both loops, off = no instruction/
 # reminder/segment, on = instruction + 2 reminders + PLATEAU segment). NO bench arm yet. evidence: R210 v39a layout-config-recreation2 (483 iterations, 5.3 h).
+# [LEDGER 2026-10-02 @4.124.43] DARK — BUILT + unit-tested: new mode `status` = boot instruction + metric tracking + STATUS score segment ONLY
+# (segment without the ` — PLATEAU` label); the detector runs on the same cadence (same cap/spacing) but steers NO reminder — each would-be
+# firing is banked as plateau_detected {name, dir, best, improvementPct, points, firing, iteration, streaming} so a run measures when `on`
+# would have fired. on / off unchanged (plateauStop.test.ts mode cases). NO bench arm yet. Values: off | on | status.
 #CORTEX_PLATEAU_STOP=
 # [LEDGER 2026-10-02 @4.124.41] DARK — default 0.002 (0.2%) relative; untested on a bench. evidence: R210 v39a layout (840,636 → 851,547 over 5.3 h; per-window gains not yet measured).
 #CORTEX_PLATEAU_REL=
@@ -1136,6 +1140,31 @@ CORTEX_ENDTURN_GATE=true
 # endturn_resolver gains {verifyScale}. Needs CORTEX_ENDTURN_RESOLVER=true.
 # [LEDGER 2026-10-01 @4.124.40] DARK — BUILT + unit-tested (endTurnResolver.test.ts R208 cases). NO bench arm yet.
 #CORTEX_VERIFY_SCALE=
+# CORTEX_RULE_INPUTS / CORTEX_RULE_INTERP / CORTEX_RULE_HOLDOUT / CORTEX_RULE_INDEP — R211–R214 HB-TASK-RULES (DARK, 2026-10-02). TB4.0
+# requirement-miss pass over the 16 never-passed tasks that fail ONE identical hidden test every run: an input field ignored or a given
+# constant altered to make the problem feasible; an ambiguous convention settled by heuristic while the right alternative sat in the
+# agent's own caveats; passing the visible sample / own oracle while hidden variants fail; producer = verifier with measured discrepancies
+# left unreconciled. Four general rules, each its own flag (off | on) so they can be A/B'd, each with TWO carriers (training/taskRules.ts):
+# A planner — one doctrine bullet per active rule in the lift-plan persona (plannerSystem; one combined block just before the output
+# instruction, after the CORTEX_LIFT_PLAN_SCOPE bullet), so the plan carries the step; B judge — one rubric clause per active rule appended to
+# the EndTurn judge persona after the R208 scale item (resolverSystemPrompt): evidence that does not establish the rule is a GAP with a
+# concrete CHECK. All off → both personas byte-identical. The rules only ask for MORE verification. Events: task_rule_plan {rules,
+# blockChars, planChars, retire} once per session when the delivered plan was written under them; task_rule_judge {surface, rules,
+# clauseChars, roundsUsed, meets, parsed, confidence} per adjudication; endturn_resolver gains {taskRules}. Carrier A needs
+# CORTEX_LIFT_PLAN on; carrier B needs CORTEX_ENDTURN_RESOLVER=true.
+# R211 INPUTS = L1 input-coverage audit: every field/column/parameter of the provided inputs accounted for; given constants never changed.
+# [LEDGER 2026-10-02 @4.124.43] DARK — BUILT + unit-tested (taskRules.test.ts: off = byte-identical planner + judge personas). NO bench arm yet. evidence: tb4-never-passed-2026-10-02 (cargo-flight-dispatch, data-anonymization, live-database-cutover).
+#CORTEX_RULE_INPUTS=
+# R212 INTERP = L2 interpretation enumeration: named alternatives each computed; keep the one consistent with every explicit hint and all data.
+# [LEDGER 2026-10-02 @4.124.43] DARK — BUILT + unit-tested (taskRules.test.ts). NO bench arm yet. evidence: tb4-never-passed-2026-10-02 (foodstuff-beta-activity, glycan-ms2-elucidation, hof-topology-interpenetration, ontology-kg-querying).
+#CORTEX_RULE_INTERP=
+# R213 HOLDOUT = L3 held-out / variant validation: when hidden inputs or generalisation are implied, validate beyond the visible sample.
+# [LEDGER 2026-10-02 @4.124.43] DARK — BUILT + unit-tested (taskRules.test.ts). NO bench arm yet. evidence: tb4-never-passed-2026-10-02 (bun-sourcemap-leak, sound-change-cascade, session-window-debug).
+#CORTEX_RULE_HOLDOUT=
+# R214 INDEP = L4 independent verifier: final check must not reuse the producing logic; unreconciled measured discrepancy blocks the finish;
+# run the task's own verification commands/limits.
+# [LEDGER 2026-10-02 @4.124.43] DARK — BUILT + unit-tested (taskRules.test.ts). NO bench arm yet. evidence: tb4-never-passed-2026-10-02 (layout-config-recreation, retro-console-soc, satb-audio-transcription).
+#CORTEX_RULE_INDEP=
 # CORTEX_TURN_CONTRACT — HB-TURN-CONTRACT (4.115.0, 2026-09-17; Terminus-2 disparity "suppress vs channel"). The boot-minimal door SUPPRESSES
 # deliberation ("Prefer acting over deliberating"; tuned at effort low). At effort high the model fought it: tb4-flash-v3 had 58 turns in
 # 23 sessions reason to the 65536 cap and emit nothing (R153). Terminus 2 CHANNELS deliberation: think freely, then every response must

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.124.42",
+  "version": "4.124.43",
   "description": "Nexus Cortex CLI - Terminal interface for multi-provider LLM orchestration",
   "main": "dist/index.js",
   "type": "module",
@@ -19,7 +19,7 @@
     "prepack": "node ../../scripts/copy-pkg-cortex-scaffold.mjs"
   },
   "dependencies": {
-    "@nexus-cortex/core": "4.124.42",
+    "@nexus-cortex/core": "4.124.43",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",