@nexus-cortex/cli 4.91.1 → 4.92.0

package/.env.example

@@ -406,6 +406,48 @@ ENABLE_DEFERRED_TOOL_LOADING=true
 # still opt a specific model out. Precedence: card > this env > default.
 # [LEDGER 2026-09-02 @4.89.0] env baseline false; ON via the deepseek CARDS (card > env) — A′: harmless-but-unproven (flips lacked mechanism; nudge ignored on wins). Operator chose to keep.
 CORTEX_LIFT_NUDGE=false
+#   CORTEX_LIFT_PLAN — mentor-as-bounded-planner (LIFT_MENTOR_PLANNER spec). At the same anchor-lift
+#   boundary, a bounded max-reasoning mentor plans the task ONCE: adversarial analysis of the prompt
+#   + confirm the REAL grader criteria (not the model's own tests) + a criteria-anchored numbered
+#   plan, or a RETIRE plan for a doomed task. Delivered as a system-reminder on the first tool_result
+#   (orchestrator-direct-invoke — NOT a forced tool call, which DeepSeek ignores post-turn-0). The
+#   narrow-door model resumes into the plan; the overthinking is quarantined in the mentor's single
+#   bounded call. Targets the two measured failure classes: grind-to-wall (14/22 flash fails → RETIRE)
+#   + self-graded success (5-7 convertible near-misses → criteria correction). Precedence: card > env > false.
+#   Runs pro @ MAX reasoning (bounded single-shot planner can't grind → max is safe + best here).
+#   INTERACTIVE GATE: fires only in headless/one-shot/bench sessions (autoApproveActions=true); in an
+#   interactive TUI a ~30-60s silent pause reads as a frozen UI, so it is SUPPRESSED unless a thinking-
+#   indicator is wired and CORTEX_LIFT_PLAN_INTERACTIVE=true.
+#   Tuning (defaults chosen from the 2026-09-04 isolated eval): CORTEX_LIFT_PLAN_EFFORT (default max),
+#   CORTEX_LIFT_PLAN_BUDGET_TOKENS (default 4000 — 🔴 at max reasoning a smaller budget is consumed
+#   entirely by reasoning_content and returns an EMPTY plan: max+1200=0 chars, max+4000=clean 2727-char
+#   plan; never token-cap tighter), CORTEX_LIFT_PLAN_TIMEOUT_MS (default 90000 — max reasoning took ~54s;
+#   fail-open to no-plan on timeout), CORTEX_LIFT_PLAN_INTERACTIVE (default false),
+#   CORTEX_LIFT_PLAN_RECON_TIMEOUT_MS (default 8000 — v1.1: before planning, the orchestrator runs a
+#   bounded read-only ENV RECON (tooling present, installed pip/npm packages, disk/mem, test files) and
+#   feeds it to the planner so it steers installs (uv/bun for MISSING packages, beyond bare boxes) and
+#   per-step Bash timeouts from the box's REAL resources; fail-open to observations alone).
+# [LEDGER 2026-09-04 @4.91.1] BUILT DARK / FIRE-CHECKED — v1 shipped gated-off (typecheck clean, planner tests, orchestrator e2e 26/26 no-regression, core build clean). LIVE FIRE-CHECK PASSED (lift_plan event fired:true/planChars>0/criteriaStated:true; negative control clean). ISOLATED EVAL: plan quality EXCELLENT at max+4000 (criteria-anchored, adversarial, anti-self-test) — but caught max+1200=empty (defaults bumped to max/4000/90s). Still UNTESTED for pass-rate lift: needs the treatment bench (grind-retire + criteria-misalign score-lift) BEFORE trusting efficacy. Adapter must add these to its env passthrough or the bench arm runs dark. Keep false.
+CORTEX_LIFT_PLAN=false
+#CORTEX_LIFT_PLAN_EFFORT=max
+#CORTEX_LIFT_PLAN_BUDGET_TOKENS=4000
+#CORTEX_LIFT_PLAN_TIMEOUT_MS=90000
+#CORTEX_LIFT_PLAN_INTERACTIVE=false
+#CORTEX_LIFT_PLAN_RECON_TIMEOUT_MS=8000
+#   CORTEX_ENDTURN_RESOLVER — the finish-side twin of the lift planner: AFTER the mechanical EndTurn gate
+#   accepts, a bounded max-reasoning mentor adjudicates "does the work product meet the task's real
+#   requirements?" MEETS finishes; GAP vetoes with a fix plan (the narrow-door model executes it instead of
+#   reasoning its way out of a mechanical rejection). Reuses the lift planner's env recon. Recommended
+#   pairing: GATE + RELAXED + resolver — the smart wrong-artifact judgment strict reached for, minus strict's
+#   bugs (likely makes strict unnecessary). Interactive-gated (same as the lift planner). Precedence card > env > false.
+#   Tuning: CORTEX_ENDTURN_RESOLVER_EFFORT (max), CORTEX_ENDTURN_RESOLVER_BUDGET_TOKENS (4000),
+#   CORTEX_ENDTURN_RESOLVER_MAX_REJECTS (2 GAP vetoes → then fallback-accept, liveness), CORTEX_ENDTURN_RESOLVER_TIMEOUT_MS (90000).
+# [LEDGER 2026-09-04 @4.92.0] BUILT DARK — mentor-as-EndTurn-judge; tsc clean, 8/8 resolver tests, orchestrator e2e 26/26 no-regression, eval-validated (caught a missing-NOT_FOUND self-graded pass + passed a correct finish). UNTESTED for pass-rate: the treatment bench = resolver ON vs OFF (both on relaxed). Keep false.
+CORTEX_ENDTURN_RESOLVER=false
+#CORTEX_ENDTURN_RESOLVER_EFFORT=max
+#CORTEX_ENDTURN_RESOLVER_BUDGET_TOKENS=4000
+#CORTEX_ENDTURN_RESOLVER_MAX_REJECTS=2
+#CORTEX_ENDTURN_RESOLVER_TIMEOUT_MS=90000
 #   CORTEX_HEADLESS_DROP_ASKUSER — in NON-INTERACTIVE sessions (stateless /v1/messages,
 #   headless API, piped oneshot) there is no human to answer AskUserQuestion, so it is a
 #   stall trap; drop it at the tool source. Kept in interactive TUIs.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.91.1",
+  "version": "4.92.0",
   "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": "4.91.1",
+    "@nexus-cortex/core": "4.92.0",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",