@nexus-cortex/cli 4.111.1 → 4.113.0

package/.env.defaults

@@ -937,6 +937,35 @@ CORTEX_ENDTURN_GATE=true
 # 9 judged passes ended on a GAP and still passed) now cost up to 4 more judge cycles — tokens, not correctness. A/B lever.
 # [LEDGER 2026-09-16 @4.111.0] BUILT + unit-tested (endTurnResolver.test.ts R160). Field: PENDING (first read on the next TB4.0 cell).
 #CORTEX_ENDTURN_RESOLVER_MAX_REJECTS_BUDGETED=
+# (no lever) R161 HB-JUDGE-TASKSHAPE (4.112.0, 2026-09-16): `isTaskShaped()` gated the EndTurn finish judge and the deadline-exit mentor
+# with a fixed coding-verb list — prompts like "Eliminate cumulative layout shift…", "To determine the beta activity…", "You are given …
+# LC-MS/MS data…" were NOT task-shaped, so 3 of the 7 patch-cell sessions (one a 353-turn finish that shipped broken) were never
+# adjudicated. Broadened verbs (eliminate/determine/identify/compute/solve/analyze/transcribe/report/produce/save/submit/…) + three
+# deliverable cues (an /app|/results|/output path; "save/write … as/to"; "N seconds to complete"). A bare question still reads false.
+# [LEDGER 2026-09-16 @4.112.0] BUILT + unit-tested (RequirementsVerification.test.ts R161). Field: PENDING.
+# (no lever) R162 HB-JUDGE-DELTA-BUILDDIRS (4.112.0, 2026-09-16): the judge's WORKSPACE DELTA capped the changed-file list at 60 BEFORE
+# skipping build/vendor dirs — sbt `target/` filled every slot on distributed-dedup and the edited SubmissionDedup.scala never reached the
+# judge (vetoes #1/#5: "source file NOT present in the WORKSPACE DELTA"). Skip dirs are now excluded in the scan itself (cap 400/200),
+# source-like files are listed first, and .cortex/.addon-tools/.ivy2/.sbt/.m2/.gradle/.npm join the skip set.
+# [LEDGER 2026-09-16 @4.112.0] BUILT + unit-tested (judgeEvidence.test.ts R162). Field: PENDING.
+# CORTEX_JUDGE_SEMANTIC / CORTEX_JUDGE_PROGRESS_MIN_CALLS / CORTEX_JUDGE_ESCALATE_REASONING — R165 HB-JUDGE-SEMANTIC (4.113.0, 2026-09-16,
+# operator: "stop hamstringing ourselves"). Three of the last four fixes were regex patches on SEMANTIC decisions (task-shape gate R161,
+# open-items phrases R151/R157, a fixed veto count R160) and each fit the last run's specimens. New split: deterministic code gathers
+# objective evidence and enforces limits; the judge decides everything semantic. SEMANTIC (default on): (1) every tool-using finish is
+# adjudicated (no task-shape regex gate; the deadline-exit mentor likewise); (2) the regex surrender/open-items nudges DEFER when the judge
+# adjudicated the finish (they remain the zero-cost path when the judge is off); (3) the judge emits `CONFIDENCE: high|medium|low` and
+# `CHECK: <cmd>` lines — the harness RUNS the named checks (bounded, up to 3) before the next adjudication and shows the results as ground
+# truth (the objective qualifier); (4) GAP is graded: low confidence with no failed check is accept-low-confidence, not a veto; (5) the veto
+# count is replaced by a PROGRESS condition — another veto needs >= PROGRESS_MIN_CALLS (3) tool calls since the last veto or a named check
+# now passing; a re-attest without progress gets ONE reasoning-on re-judge (ESCALATE_REASONING, per-surface CORTEX_ENDTURN_RESOLVER_REASONING
+# forced on for that call) and then accept-with-gap (event endturn_gap_accepted carries the plan + checks) — the R160 budgeted cap stays
+# as the ceiling. The judge prompt now carries PRIOR VETO ITEMS + harness-observed PROGRESS and must grade each prior item CLOSED/OPEN
+# first. Events: endturn_resolver gains {semantic, action, confidence, namedChecks, namedRan/Passed/Failed, callsSince, progressed, escalated}.
+# CORTEX_JUDGE_SEMANTIC=false restores the 4.111/4.112 gating byte-for-byte (the A/B control).
+# [LEDGER 2026-09-16 @4.113.0] BUILT + unit-tested (endTurnResolver.test.ts R165: parser, policy table, prompt). Field: PENDING (first read on the next cell).
+#CORTEX_JUDGE_SEMANTIC=
+#CORTEX_JUDGE_PROGRESS_MIN_CALLS=
+#CORTEX_JUDGE_ESCALATE_REASONING=
 # (no lever) 4.110.0 closes the 4.109.0 disclosures (2026-09-16): R154 image-rejection heal now also covers the STREAMING loop
 # (continuation re-streamed once after the stub; stream empty-retry and stream R29a synthesis wrapped like the non-streaming calls);
 # the sub-agent console fallback prints a progress beat only on a turn change or every 30 s (was every second: 500+ ticker lines per

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.111.1",
+  "version": "4.113.0",
   "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": "4.111.1",
+    "@nexus-cortex/core": "4.113.0",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",