@nexus-cortex/cli 4.124.11 → 4.124.12
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 +25 -0
- package/package.json +2 -2
package/.env.defaults
CHANGED
|
@@ -1135,6 +1135,28 @@ CORTEX_ENDTURN_GATE=true
|
|
|
1135
1135
|
# [LEDGER 2026-09-20 @4.121.0] BUILT + unit-tested. FIELD: pending (cell g2).
|
|
1136
1136
|
#CORTEX_JUDGE_SPEC_REPEAT_MAX=
|
|
1137
1137
|
#CORTEX_JUDGE_SPEC_TESTS_AT=
|
|
1138
|
+
# CORTEX_JUDGE_REQ_LEDGER / _MAX / _HOLD_MAX — R187 HB-REQUIREMENT-LEDGER (4.124.12, 2026-09-23; DARK, default off). The consistency
|
|
1139
|
+
# lever the top-7 read named (tb4-consistency-top7-2026-09-23.md): five of the seven tasks flash passes ≥50% of the time fail on a
|
|
1140
|
+
# requirement the TASK TEXT STATES, and the failing run finishes EARLIER with more budget left, the resolver accepting — the writer's own
|
|
1141
|
+
# checks test the path it chose. At lift a mentor call (endturn-resolver wire, pro @ max, task text + env report ONLY) extracts each stated
|
|
1142
|
+
# requirement as `REQ n | kind | text | CHECK: cmd|NONE` (training/requirementLedger.ts); the writer sees the ledger with its plan of attack
|
|
1143
|
+
# ("each line must be EXERCISED before you finish"); at every finish the harness runs the checks — FAILED = R166 veto evidence (with the
|
|
1144
|
+
# spec/named checks), OPEN (never passed nor failed) holds a finish that would otherwise stand ONCE (_HOLD_MAX), naming the open lines and
|
|
1145
|
+
# their checks; UNVERIFIABLE (CHECK: NONE) is shown to the judge only. Never below CORTEX_JUDGE_VETO_MIN_REMAINING. Events:
|
|
1146
|
+
# requirement_ledger (lines), requirement_ledger_delivered, endturn_resolver += reqLines/reqOpen/reqExercised/reqFailed/reqUnverifiable/reqHeld.
|
|
1147
|
+
# Differs from R174 spec tests (commands only, no writer-facing lines, no hold on "unexercised"). Cell: the seven tasks (n≈18 each) first.
|
|
1148
|
+
#CORTEX_JUDGE_REQ_LEDGER=
|
|
1149
|
+
#CORTEX_JUDGE_REQ_LEDGER_MAX=
|
|
1150
|
+
#CORTEX_JUDGE_REQ_LEDGER_HOLD_MAX=
|
|
1151
|
+
# CORTEX_JUDGE_REQ_LEDGER_JEV / _JEV_MIN — R187b (operator: "use jev in additional one-shot calls to verify the end turn meets the
|
|
1152
|
+
# requirements of the task"): E0 measured Jev as a WHOLE-task doneness judge at AUC 0.64 (weak; leg D, the Southbridge phase/forecast
|
|
1153
|
+
# read, no pass signal) but as a typed gate on concrete evidence at 0.98. The ledger makes doneness typed: after the shell checks, ONE Jev
|
|
1154
|
+
# call asks `met_<id>` per OPEN/UNVERIFIABLE line — "exercised AND met, judging only from the writer's attestation, the work-product tail and
|
|
1155
|
+
# the harness result" — and closes lines ≥ _JEV_MIN (0.7) with provenance `jev:`; the rest stay open (→ the hold). Jev never sees the judge's
|
|
1156
|
+
# verdict (gate independence). Default on when the ledger is on; needs TYPESAFE_API_KEY (fail-open to shell-only). Banked: reqJevAsked /
|
|
1157
|
+
# reqJevClosed / reqJevLatencyMs.
|
|
1158
|
+
#CORTEX_JUDGE_REQ_LEDGER_JEV=
|
|
1159
|
+
#CORTEX_JUDGE_REQ_LEDGER_JEV_MIN=
|
|
1138
1160
|
# CORTEX_JUDGE_INDEPENDENT_DERIVATION / _TOL — R176 HB-INDEPENDENT-DERIVATION (4.122.0, 2026-09-21; design docs/R176_INDEPENDENT_DERIVATION_DESIGN.md).
|
|
1139
1161
|
# The largest never-passed TB4.0 class (~14 tasks: foodstuff, roy-polymorph, glycan, gsea, hof, vigenere, sound-change, cargo, ctr,
|
|
1140
1162
|
# shadow-relay, satb, takens…) is a computed value / exact artifact graded against a golden answer with NO ground truth in the container:
|
|
@@ -1224,6 +1246,9 @@ CORTEX_ENDTURN_GATE=true
|
|
|
1224
1246
|
# options is handed back unexecuted unless the action carries `single_reason` (one sentence why only one action makes sense); bounded 5
|
|
1225
1247
|
# re-asks/session; the author still widens afterwards. CORTEX_FRAME_AUTHOR_MODEL (unset = HELPER_MODEL_ID = flash): set deepseek-v4-pro for
|
|
1226
1248
|
# pro-authored alternatives (thinking off). Banked: singleReason on frame_turn. E3 re-pinned 4.124.11.
|
|
1249
|
+
# [LEDGER 2026-09-23 @4.124.11] LOCAL SMOKE PASSED (E3 env, adapter-shaped request, toy CSV-sum): the writer gave 2 distinct options on every
|
|
1250
|
+
# turn under the new contract (no re-asks, no single_reason needed), the author added a 3rd, Jev's questions were pick_<id> only (5 keys), it
|
|
1251
|
+
# chose the AUTHOR's option on turn 3 (0.81, ran rc 0) and FINISH on turn 4 (0.62); sum correct in 4 turns.
|
|
1227
1252
|
#CORTEX_FRAME_KEY_GUARD=
|
|
1228
1253
|
#CORTEX_FRAME_MIN_CANDIDATES=
|
|
1229
1254
|
#CORTEX_FRAME_AUTHOR=
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@nexus-cortex/cli",
|
|
3
|
-
"version": "4.124.
|
|
3
|
+
"version": "4.124.12",
|
|
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": "4.124.
|
|
22
|
+
"@nexus-cortex/core": "4.124.12",
|
|
23
23
|
"chalk": "^4.1.2",
|
|
24
24
|
"cli-spinners": "^2.9.0",
|
|
25
25
|
"commander": "^11.0.0",
|