@nexus-cortex/cli 4.107.1 → 4.107.2

package/.env.defaults

@@ -281,6 +281,7 @@ CORTEX_EFFORT_TAIL=false
 #   accepted but COERCED → 'high' server-side, so the card default 'medium' effectively runs HIGH.
 #   ⇒ the flash-low verdict was low-vs-HIGH (not low-vs-medium): ~30% cheaper at pass-rate WASH.
 #   Applies to the ACTION model here; the mentor roles run 'max' (top), the helper middleware runs 'none'.
+# [LEDGER 2026-09-11 @4.107.0] cell-n-r4 (hard core 13×K=2, flash action model, FINAL 47/52 rows): high = NO LIFT — ah-none 6/22 (0.27), ah-low 7/25 (0.28) vs control 11/26 (0.42); +3.5–4.5 min/task latency, turns unchanged (narrow door intact). Keep unset (card default). DARK. Ledger r-cell-n-r34.
 #CORTEX_ACTION_EFFORT=
 # Trigger helper-model review on tool errors (only applies when mentorship is enabled)
 MENTORSHIP_TRIGGER_ON_ERROR=false
@@ -332,6 +333,7 @@ MENTORSHIP_HELPER_MODEL=deepseek-flash
 #   CORTEX_MENTOR_EFFORT — low|medium|high|max. ONE effort for every planner surface (the mentor-effort A/B lever); a
 #   surface's own *_EFFORT (CORTEX_LIFT_PLAN_EFFORT etc.), when explicitly set, wins over it. Empty = per-surface (max).
 # [LEDGER 2026-09-10 @4.105.0] unset — cell-m A/Bs {pro, deepseek-flash} × {low, high, max} (+ thinking-off baselines).
+# [LEDGER 2026-09-11 @4.107.0] cell-n-r3 flash@low (REASONING=on): REJECT — delivery 91% thinking-on (the treatment fired) but false-accept 0.67 (worst measured; high 0.56, max 0.50, off 0.33) and 6/24 vs control 11/26. Effort is monotone in cost only; ANY thinking on the resolver raises false accepts. Moot while REASONING=none (k=5). DARK. Ledger r-cell-n-r34.
 #CORTEX_MENTOR_EFFORT=
 # [LEDGER 2026-09-10 @4.105.0] cell-m pilot: low/high/max UNMEASURABLE — the thinking-on calls came back empty (see CORTEX_MENTOR_REASONING). Only flash@low ever delivered (1/4 plans, 2/3 verdicts). Re-test after HB-MENTOR-BUDGET.
 #   CORTEX_ASK_FOR_ADVICE — true|false. Include the model-initiated AskForAdvice consult tool while mentorship is on.
@@ -366,6 +368,14 @@ MENTORSHIP_HELPER_MODEL=deepseek-flash
 # [LEDGER 2026-09-11 @4.107.0] BUILT; first bench test = cell-n-r1 arm `fh-plan` (CORTEX_LIFT_PLAN_REASONING=on +
 #   CORTEX_ENDTURN_RESOLVER_REASONING=none under CORTEX_MENTOR_REASONING=none).
 #CORTEX_LIFT_PLAN_REASONING=
+# CORTEX_LIFT_PLAN_DOCTRINE — planner doctrine version: v1 (default; the 4.107.0 PLANNER_SYSTEM) | v2 (adds the four
+#   cell-n-r1 census bullets: ONE INSTALL LAYER/uv, LONG WAITS ≤60 s polls, EXACT-OUTPUT byte-level, EXPECTED LITERALS ARE
+#   LAW + graders re-parameterize). Prompt-only.
+# [LEDGER 2026-09-11 @4.107.2] LEVER (was hard-wired ON in 4.107.1). cell-n-r5 (4.107.1 control, hard core): 4/18 vs 11/26 on
+#   4.107.0, PAIRED 6 losses / 1 gain, fewer turns on 12/18 tasks (finishes earlier, less verification: gcode read "gcodo3"
+#   without the control's max-zoom check). Shipped together with EndTurn essential, so attribution needs the 2×2 (cell-n-r6:
+#   base / et-ess / doc-v2 / et-doc). Default v1 = measured baseline until the 2×2 decides.
+#CORTEX_LIFT_PLAN_DOCTRINE=
 # [LEDGER 2026-09-11 @4.107.0] cell-n-r1 arm fh-plan (LIFT_PLAN_REASONING=on @high + resolver none): 7/25 vs control 10/24 — the thinking-on planner did not help on the hard core. DARK.
 #CORTEX_ENDTURN_RESOLVER_REASONING=
 #CORTEX_DEADLINE_EXIT_MENTOR_REASONING=
@@ -709,6 +719,13 @@ ROUTER_MIN_SAMPLES=3
 # [LEDGER 2026-09-03 @4.91.0] DARK/PENDING → **RECOMMENDED ON for k=5 (with REQUIREMENTS=strict)** — 4.91.0: gates now run on the STREAMING path too (were sendMessage-only; one shared endTurnGates.ts, live-proven on stream:true) and Stage-2 grounding accepts text the model WROTE this turn (Write/Edit content) — the false 'not grounded' rejections on authored files are gone. COST (v4 pass mining + doctrine-mine): every pass paid 4-8 EndTurn round-trips, the biggest share = Stage-2 CITATION rejects (17/43 doctrine findings; the model never re-ran a command for a fresh verbatim line) → 4.90.2 nudge teaches per-turn grounding + re-run; expect controls' +25-35% turn tax to drop — measure at k=5. — v4 (n=1, @4.90.0): gate engaged heavily under strict (flash gate_req=22/cite=13, pro 17/4), controls bn-fit+sqlite held on BOTH models, pro flips vs p3: dna-insert, pytorch-model-cli, cancel-async (n=1 candidates). Prior 3 cells: 4.71 fp 11→1 · fd +2/5 · c3 (n=2, r-c3-candidate-config) code-from-image FLIP 2/2 (first flash-family pass ever; Stage-4 requirement rejections, no mentor) + dna-insert 1/2; 0 clean regressions outside its LIMIT (accepts a re-attested wrong artifact: pytorch-model-cli r2, dna-insert fd). Cost: attestation turns. Operator decision pending. PRO (r-p3, n=1): controls 3/3 held with NO attestation tax (bn-fit 53→30 turns), 0 regressions, 0 paralysis; 0/13 flips on pro's hard core (budget timeouts while working). → k=5 config for BOTH models: guards + GATE+REQ + ENABLE_WEBTOOLS=false, mentor/tail off.
 # [LEDGER 2026-09-06 @4.93.0] ON (reson standard baseline). GATE+REQ (with REQUIREMENTS=true, NOT strict) shipped as the shared reson baseline through resolver-k5 — proven net-positive as a stack. k5 held GATE on in both arms; prior cell evidence stands. Part of the standard.
 CORTEX_ENDTURN_GATE=true
+# CORTEX_ENDTURN_TIER — EndTurn discovery tier: standard (default; deferred behind SearchTools, the 4.107.0 baseline) |
+#   essential (in the turn-1 tool set; no SearchTools hunt for the mandatory finish tool).
+# [LEDGER 2026-09-11 @4.107.2] LEVER (was hard-wired essential in 4.107.1 after the cell-n-r1 census: 70–80% of sessions spent a
+#   SearchTools call hunting EndTurn, 11 tried Task as a finish tool). MECHANISM PROVEN on cell-n-r5: SearchTools 21→2, Task 3→0 —
+#   but the hard core REGRESSED (4/18 vs 11/26) with fewer turns per task: a more salient finish tool may end turns EARLY.
+#   Shipped with the planner doctrine, so the 2×2 (cell-n-r6) attributes it. Default standard = baseline until then.
+#CORTEX_ENDTURN_TIER=
 # Stage 4 (4.70.0, requires the gate ON): task-requirements attestation —
 # enumerate each stated requirement with what satisfies it + how it was
 # verified; mutating turns with no checks are challenged. Default OFF.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.107.1",
+  "version": "4.107.2",
   "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": "4.107.1",
+    "@nexus-cortex/core": "4.107.2",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",