@nexus-cortex/cli 4.120.0 → 4.121.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.env.defaults +19 -0
- package/package.json +2 -2
package/.env.defaults
CHANGED
|
@@ -1111,6 +1111,25 @@ CORTEX_ENDTURN_GATE=true
|
|
|
1111
1111
|
# [LEDGER 2026-09-20 @4.120.0] BUILT + unit-tested (R174 block in endTurnResolver.test.ts). FIELD: pending (cell g1).
|
|
1112
1112
|
#CORTEX_JUDGE_SPEC_TESTS=
|
|
1113
1113
|
#CORTEX_JUDGE_SPEC_TESTS_MAX=
|
|
1114
|
+
# CORTEX_JUDGE_VETO_MIN_REMAINING / _GAP_HOLD_MIN_INTERVAL_MS / _GAP_HOLD_PLAN_MAX_SIMILARITY — R173c (4.121.0, 2026-09-20, cell g1
|
|
1115
|
+
# attribution r-tb4-g1-2026-09-20.md §3): the ONE attributable regression was an evidence veto at 15% budget (27 min left → fail; control's
|
|
1116
|
+
# judge accepted at 25% and passed); the three 6-hold failures re-finished six times inside 2–4% of the budget (the ≥3-call progress rule
|
|
1117
|
+
# passed while no work happened). Floor: below _MIN_REMAINING (0 = off; cell g2 arm: 0.25) no veto/hold of any kind — the gap is recorded
|
|
1118
|
+
# (event += belowFloor). Progress: a RE-hold needs ≥ _MIN_INTERVAL_MS (180000) since the last hold OR a plan whose token-Jaccard vs the
|
|
1119
|
+
# prior plan is < _PLAN_MAX_SIMILARITY (0.6); otherwise the R165 no-progress path (escalate once, then accept). Event += {holdProgressed,
|
|
1120
|
+
# msSinceLastHold}. The 4 pass flips (holds at ≥ 66% budget) are untouched by both.
|
|
1121
|
+
# [LEDGER 2026-09-20 @4.121.0] BUILT + unit-tested. FIELD: pending (cell g2).
|
|
1122
|
+
#CORTEX_JUDGE_VETO_MIN_REMAINING=
|
|
1123
|
+
#CORTEX_JUDGE_GAP_HOLD_MIN_INTERVAL_MS=
|
|
1124
|
+
#CORTEX_JUDGE_GAP_HOLD_PLAN_MAX_SIMILARITY=
|
|
1125
|
+
# CORTEX_JUDGE_SPEC_REPEAT_MAX / _SPEC_TESTS_AT — R174b (4.121.0): g1 read — 4 of the 8 passing lever sessions had a "failing" spec check
|
|
1126
|
+
# (false failures; protein-autointerp drove 6 holds on two wrong checks). A spec check that FAILS with the identical first output line at
|
|
1127
|
+
# _SPEC_REPEAT_MAX (2) consecutive adjudications while no OTHER check failed is `suspect`: shown to the judge with a caveat, not veto
|
|
1128
|
+
# evidence (event += specSuspect). _SPEC_TESTS_AT=lift authors the checks in the background at task lift (formal-crypto's first finish
|
|
1129
|
+
# came at 12% budget; at finish the checks arrived too late to matter); default finish = 4.120.0 behaviour.
|
|
1130
|
+
# [LEDGER 2026-09-20 @4.121.0] BUILT + unit-tested. FIELD: pending (cell g2).
|
|
1131
|
+
#CORTEX_JUDGE_SPEC_REPEAT_MAX=
|
|
1132
|
+
#CORTEX_JUDGE_SPEC_TESTS_AT=
|
|
1114
1133
|
# (no lever) R169 HB-NEARDUP-SCRATCH-STEM — REFUTED before shipping (2026-09-17, pilot-12 trajectory replay). The distiller's 16
|
|
1115
1134
|
# "repeated-identical-retry" candidates were re-read: the two stuck sessions (coq-block-bound base arm: `cat > /tmp/tN.v <<EOF` with a
|
|
1116
1135
|
# DIFFERENT proof body each attempt; rs-archive-clone: 191 distinct `python3 -c` bodies) are unconverged EXPLORATION, not retries —
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@nexus-cortex/cli",
|
|
3
|
-
"version": "4.
|
|
3
|
+
"version": "4.121.0",
|
|
4
4
|
"description": "Nexus Cortex CLI - Terminal interface for multi-provider LLM orchestration",
|
|
5
5
|
"main": "dist/index.js",
|
|
6
6
|
"type": "module",
|
|
@@ -19,7 +19,7 @@
|
|
|
19
19
|
"prepack": "node ../../scripts/copy-pkg-cortex-scaffold.mjs"
|
|
20
20
|
},
|
|
21
21
|
"dependencies": {
|
|
22
|
-
"@nexus-cortex/core": "4.
|
|
22
|
+
"@nexus-cortex/core": "4.121.0",
|
|
23
23
|
"chalk": "^4.1.2",
|
|
24
24
|
"cli-spinners": "^2.9.0",
|
|
25
25
|
"commander": "^11.0.0",
|