@nexus-cortex/cli 4.94.0 → 4.96.1

package/.env.defaults

@@ -261,6 +261,12 @@ CORTEX_EFFORT_TAIL=false
 # never medium-vs-low). Floor risk: too low loses in-loop tool micro-reasoning. Arm in the fanout
 # cell (pro@low vs pro@medium vs pro@max action, mentors@max); winner → bake into the pro card's
 # reasoning.effortByRole.action (validate-then-bake).
+# [LEDGER 2026-09-07 @4.94.0] DARK/PENDING (n=1, dark-levers dlelo/dlemx + pro-effort pelo/pemd/pemx):
+#   low = FLASH EFFICIENCY WIN (dlelo 33 turns/34.6K outTok/$1.635 vs dlctl 44/54.6K/$2.315, no pass
+#   loss); max = REJECT (over-deliberates; pro@max pemx CUT mid-run — failed control at 67 turns/2x
+#   tokens). PRO low≈medium too close (pe-lo/pe-md torn down at egress-rot). ⇒ flash-low confirmed at
+#   n=1 → card reasoning.effortByRole.action bake pending k=5; pro-track k=5 (low vs med, mentors@max)
+#   STILL OWED. Do NOT ship-on: n=1, k=5-gated. Stays dark/UNSET in production.
 #CORTEX_ACTION_EFFORT=
 # Trigger helper-model review on tool errors (only applies when mentorship is enabled)
 MENTORSHIP_TRIGGER_ON_ERROR=false
@@ -488,7 +494,34 @@ CORTEX_ENDTURN_RESOLVER=true
 # [LEDGER 2026-09-06 @4.93.0] DARK/PENDING — built (resolver v2 abstention axis); addresses the k=5
 #   over-rejection finding (filter-js 7 rej/0 pass, pytorch 8 rej/1 pass). NOT yet validated live —
 #   arm in the next fanout cell (measure cost-per-PASS + false-RETIRE rate vs resolver-without-abstain).
-#CORTEX_ENDTURN_RESOLVER_ABSTAIN=false
+# [LEDGER 2026-09-07 @4.94.0] DARK/PROMISING (n=1, dark-levers dlabs vs dlctl): equal pass (7=7),
+#   ~30% CHEAPER ($1.53 vs $2.32), MECHANISM-ATTRIBUTABLE — decisions.jsonl shows abstain/RETIRE fired
+#   on the reject-loop tasks (filter-js abstain×2/retire×3, pytorch abstain×1, sqlite-gcov abstain×1).
+#   Thesis confirmed (stops burning pro@max re-rejecting doomed finishes).
+# [LEDGER 2026-09-07 @4.94.0 — SHIP-ON, operator decision] 🟢 ON (reson STANDARD). Flipped default-on
+#   from the n=1 PROMISING verdict (equal pass, ~30% cheaper, mechanism-attributable). Rationale
+#   (operator): affirm-then-verify, not gate-then-ship — budget doesn't allow adversarially EXCLUDING
+#   a promising optimization vs AFFIRMING it. k=5 now CONFIRMS rather than gates (pins the published
+#   version → re-measures ABSTAIN on current code). Orthogonal to this session's other changes: the
+#   resolver/adjudicateEndTurn path reads task/env/workProduct/attestation only — NO classifyToolOutcome/
+#   failure-count/loop-block coupling (grep-verified); loop-block ships dark (no-op); distiller = tooling.
+#   ROLLBACK if k=5 shows a net regression or a high false-RETIRE rate.
+CORTEX_ENDTURN_RESOLVER_ABSTAIN=true
+#
+# CORTEX_EMPTY_TURN_CONTINUE — the HB-ENDTURN-TERMINAL fix (operator design 2026-09-08). The EndTurn
+# gate's terminal "you stopped — write your answer, do NOT call any tools" reminder can fire on a
+# reasoning-only mid-recon turn (the model thought but emitted no tool call yet), forbidding recovery
+# and cutting a build one turn short — the dominant DeepSeek premature-surrender pattern. When on, a
+# reasoning-only empty turn that STILL HAS BUDGET (<60% of the per-turn wall-clock deadline AND <60% of
+# max tool-iterations) is classified `reasoning_only_active` (mirrors the D-E `truncated` carve-out) and
+# gets a bounded (×3) "continue with tools — you still have budget" nudge instead of the terminal
+# surrender. Applies to both the non-stream and stream loops (stream reuses the EndTurn gate's
+# re-request mechanism). NOT the loop-block lever (proven: the terminal reminder fires in control arms;
+# loop_tool_block fired 0× in k5v2). Flag off = byte-identical.
+# [LEDGER 2026-09-08 @4.96.1] DARK (default false) — BUILT + tsc-clean + emptyResponseClassifier 19/19 +
+# emptyTurnContinue integration 4/4 (both loops flag-on continue+resume, flag-off terminal, budget-spent
+# regression guard) + reexecutionGuard regression check. Ships dark; efficacy A/B still owed.
+#CORTEX_EMPTY_TURN_CONTINUE=true
 #
 #   CORTEX_DEADLINE_EXIT_MENTOR — the "smart deadline". At the WARN rung (~0.9 of the per-turn
 #   wall-clock deadline, where residual still exists), a bounded mentor decides what to do with the
@@ -502,6 +535,11 @@ CORTEX_ENDTURN_RESOLVER=true
 #   deadline adjudication, NOT the mis-premised endturn_gate_fallback). Addresses budget_frac>1.0
 #   overrun + last-fifth grind. 🔴 quality-gated (tell "closing in" from "grinding") — arm in the next
 #   fanout cell; measure pass-rate + budget_frac on the 0.80-1.0 finishing population.
+# [LEDGER 2026-09-07 @4.94.0] DARK/RE-TARGET (n=1, dark-levers dldln): FIRED (make-mips×2, schemelike×1)
+#   but its only +1 flip (pytorch) was on a task where it did NOT fire = noise; no attributable gain,
+#   +cost (59 turns). Its "don't-truncate-late-win" value needs the 0.80-1.0 FINISHING population
+#   specifically, not this reject-loop-heavy subset. ⇒ keep dark; re-target the k=5/next cell to the
+#   high-budget_frac finishers (schemelike/make-mips/install-windows/filter-js/pytorch). Stays false.
 #CORTEX_DEADLINE_EXIT_MENTOR=false
 #CORTEX_DEADLINE_EXIT_MENTOR_EFFORT=max
 #CORTEX_DEADLINE_EXIT_MENTOR_BUDGET_TOKENS=2000
@@ -883,6 +921,24 @@ CORTEX_ORIENT_BOOTSTRAP=1
 # [LEDGER 2026-09-02 @4.89.0] code default 12 (4.88.0) — 8 misfired on persistence-wins grinds (rstan-to-pystan regressed both arms).
 #NEARDUP_NUDGE_AT=12
 
+# CORTEX_LOOP_TOOL_BLOCK — hard loop intervention (operator design 2026-09-07). On a ladder-detected
+# non-converging loop (diversify/break), disables the LOOPING TOOL'S EXECUTOR for one turn (cache-safe:
+# the tool stays in the list, so the prompt cache is NOT busted) and returns an append-only redirect
+# error steering to the complementary tools (Bash→Read/Write/Edit, Edit→Read/Bash). After 2 blocks that
+# do not break the loop, ESCALATES to a bounded pro-max exit-planner mentor (orchestrator-direct-invoke,
+# NOT forced tool_choice — dead on DeepSeek mid-history; the 4th sibling of the endturn-resolver family)
+# that reads the last loop calls + their outputs and returns VERDICT: REPLAN <different plan> | RETIRE
+# <stop, record best-effort>.
+# [LEDGER 2026-09-07 @unreleased] DARK (default false) — BUILT + tsc-clean + loopToolBlock 6/6 +
+# loopExitPlanner 9/9 + orchestrator e2e 26/26 + LIVE-SEEDED FIRE-CHECK PASSED (seeded grep-loop:
+# block#1 → block#2 → ESCALATED → exit-planner RETIRE delivered, model complied + stopped retrying Bash).
+# Ships dark on the combined release; efficacy A/B still owed (retry_loop is the dominant TB2 fail class).
+#CORTEX_LOOP_TOOL_BLOCK=true
+# Escalation exit-planner mentor tuning (bounded pro-max; only consulted when CORTEX_LOOP_TOOL_BLOCK=true).
+#CORTEX_LOOP_TOOL_BLOCK_EFFORT=max           # a bounded single-shot planner cannot grind
+#CORTEX_LOOP_TOOL_BLOCK_BUDGET_TOKENS=4000   # big enough that reasoning does not eat the plan on DeepSeek
+#CORTEX_LOOP_TOOL_BLOCK_TIMEOUT_MS=90000     # fail-open to the generic redirect on timeout
+
 
 # --- OPTIMAL LIFT CONFIG (appended) ---
 # [LEDGER 2026-09-02 @4.90.0] DEAD — no code path reads CORTEX_IDLE_TIMEOUT (grep packages/*/src = 0 hits); it was cargo-culted into the bench adapter env for months and removed there in adapter v21 (p3 timeout audit). Left commented so nobody re-adds it as a "lever".

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.94.0",
+  "version": "4.96.1",
   "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": "4.94.0",
+    "@nexus-cortex/core": "4.96.1",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",