@nexus-cortex/cli 4.124.40 → 4.124.42

package/.env.defaults

@@ -1003,6 +1003,35 @@ CORTEX_ENDTURN_GATE=true
 # per orchestrator. Event pid1_guard {noted, pid1Cmd, children, chars} when the note is added. off: nothing read, nothing added.
 # [LEDGER 2026-10-01 @4.124.40] DARK — BUILT + unit-tested (pid1Guard.test.ts: fake /proc builder cases). NO bench arm yet.
 #CORTEX_PID1_GUARD=
+# CORTEX_PLATEAU_STOP / _REL / _WINDOW / _MIN_POINTS — R210 HB-PLATEAU-STOP (DARK, 2026-10-02). v39a layout-config-recreation2: the
+# agent cannot see the grader's pass threshold on an optimization task, so it polished a self-computed score for 5.3 h (483 iterations,
+# 840,636 → 851,547 with ever-finer searches); budget steering reports time left, never "enough". Operator design = a PLATEAU VARIATION
+# TARGET. on: at the first tool_result boundary (same carrier as the R209 PID 1 note) ONE system-reminder asks the model, when optimizing
+# a measurable objective, to print `PLATEAU_METRIC <name>=<number> dir=<max|min>` after every evaluation and keep the deliverable at its
+# best result. Every tool round, the tool_result texts are scanned for that line (last occurrence per result wins); a per-session series
+# is kept per metric name (orchestrator/plateauStop.ts). Plateau = n >= MIN_POINTS and the best of the last WINDOW reports improves on
+# the best before them by < REL, relative (max: (bestRecent-bestBefore)/|bestBefore|; min inverted; a series that got worse counts).
+# The first plateau steers ONE reminder on the budget-steering channel (appended to the round's first tool_result, steering_injected
+# kind 'plateau'): "PLATEAU: your <name> improved only <x>% over the last <window> evaluations (target ≥ <rel>%). Stop optimizing.
+# Make sure the deliverable holds the best result (<best>), run the task's own verification/tests once, then finish." At most 2 per
+# session; the second only after >= WINDOW more reports with still no real gain. Events: plateau_metric_seen {name, dir, value} (once
+# per metric name), plateau_stop {name, dir, best, improvementPct, points, firing}. STATUS segment (with CORTEX_TURN_STATUS on): once a
+# metric was reported, the per-turn STATUS line gains ONE segment for the most recently reported metric — `score <name>: best <v> (<n>
+# evals); +<x>% over last <window> (target ≥<rel>%)`, plus ` — PLATEAU` while the detector says plateau (improvement part only once the
+# series is comparable). No metric seen or lever off → STATUS byte-identical. off: no instruction, results not scanned, no segment.
+# REL = relative-improvement target (default 0.002 = 0.2%); WINDOW = most recent reports compared (default 6); MIN_POINTS = reports
+# needed before any stop can fire (default 8). Bad values fall back to the defaults.
+# [LEDGER 2026-10-02 @4.124.41] DARK — BUILT + unit-tested (plateauStop.test.ts: detector rising/flat/worse/min/min-points/window edges,
+# [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).
+#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=
+# [LEDGER 2026-10-02 @4.124.41] DARK — default 6 reports; untested on a bench. evidence: R210 v39a layout.
+#CORTEX_PLATEAU_WINDOW=
+# [LEDGER 2026-10-02 @4.124.41] DARK — default 8 reports; untested on a bench. evidence: R210 v39a layout.
+#CORTEX_PLATEAU_MIN_POINTS=
 # (no lever) R154 HB-IMAGE-REJECTION-HEAL (4.109.0, 2026-09-16): retro-console-soc generated a 128x128 8-bit GRAYSCALE PNG, called
 # ReadImage, and DeepSeek answered the next continuation with `400 .messages[290].image[0]: You have uploaded an unsupported image`;
 # the exception escaped after the tool batch, the already-executed guard left the loop, and the R29a synthesis failed on the same block —

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.124.40",
+  "version": "4.124.42",
   "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": "4.124.40",
+    "@nexus-cortex/core": "4.124.42",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",