@nexus-cortex/cli 4.114.2 → 4.116.0
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 +26 -0
- package/package.json +2 -2
package/.env.defaults
CHANGED
|
@@ -984,6 +984,32 @@ CORTEX_ENDTURN_GATE=true
|
|
|
984
984
|
# hold a finish. Event field namedInconclusive.
|
|
985
985
|
#CORTEX_JUDGE_VETO=
|
|
986
986
|
#CORTEX_JUDGE_EVIDENCE_MAX_VETOES=
|
|
987
|
+
# CORTEX_TURN_CONTRACT — HB-TURN-CONTRACT (4.115.0, 2026-09-17; Terminus-2 disparity "suppress vs channel"). The boot-minimal door SUPPRESSES
|
|
988
|
+
# deliberation ("Prefer acting over deliberating"; tuned at effort low). At effort high the model fought it: tb4-flash-v3 had 58 turns in
|
|
989
|
+
# 23 sessions reason to the 65536 cap and emit nothing (R153). Terminus 2 CHANNELS deliberation: think freely, then every response must
|
|
990
|
+
# carry analysis + plan + the action, and a length-truncated turn is re-issued at the SAME effort with an explicit "none of your actions
|
|
991
|
+
# were performed, you exceeded N tokens, re-issue in smaller steps" message. =channel: the boot prompt drops the suppression clause and
|
|
992
|
+
# appends the ANALYSIS/PLAN/action contract; the R153 exhaustion nudge becomes the Terminus message (cap named) and the effort backoff
|
|
993
|
+
# defaults OFF (CORTEX_REASONING_EXHAUST_BACKOFF=true overrides). '' (default) = the shipped door, byte-identical. Probe 2026-09-17:
|
|
994
|
+
# DeepSeek has NO hard reasoning budget (thinking.budget_tokens / max_reasoning_tokens ignored; reasoning_effort is the only soft lever;
|
|
995
|
+
# reasoning counts inside max_tokens and starves the answer) — both harnesses hit the same wall; this lever changes the RECOVERY and the FRAME.
|
|
996
|
+
# [LEDGER 2026-09-17 @4.115.0] BUILT + unit-tested (turnContract.test.ts). Field: PENDING (tb4 pilot-12, channel arm at effort max).
|
|
997
|
+
#CORTEX_TURN_CONTRACT=
|
|
998
|
+
# CORTEX_FINISH_CONFIRM / CORTEX_FINISH_CONFIRM_MIN_REMAINING / CORTEX_FINISH_CONFIRM_MAX — R167 HB-FINISH-CONFIRM (4.116.0, 2026-09-17,
|
|
999
|
+
# pilot-12 hand-curation). The early-finish class is the whole game on the confident-wrong tail: 8/12 first finish attempts per arm
|
|
1000
|
+
# had >= 70% of the wall budget left (Terminus 2 too: 8/12 confident-wrong finishes in 15–105 min, its bare "are you sure" changed
|
|
1001
|
+
# nothing). Two grounded defects: (1) R165 deferred the budget-continue/surrender nudges whenever the judge adjudicated, INCLUDING
|
|
1002
|
+
# accept-with-gap — coq-block-bound surrendered honestly ("I did not complete the task", Admitted remains) at 73% budget left and
|
|
1003
|
+
# nothing pushed back; (2) the judge's accept-with-gap plans named REAL gaps (mvcc: `make repro` never run; hof: invalid CS;
|
|
1004
|
+
# rs-archive: malformed-input mismatches; coq: Admitted) that were recorded and never shown to the model. FIX: when the judge would
|
|
1005
|
+
# accept WITH a gap and >= MIN_REMAINING (0.3) of the budget remains, the finish is HELD once (MAX=1) with a zero-model-call
|
|
1006
|
+
# confirmation carrying the budget left, the reviewer's plan (advisory) and the junior's own open_items; the next EndTurn stands
|
|
1007
|
+
# unless an evidence veto (R166) applies. An accept-with-gap no longer silences the R151/R157 nudges (judgeOwnsFinish excludes it).
|
|
1008
|
+
# Event: finish_confirm {action, remainingFrac, confirms, planChars, openItems}. =false restores 4.115.0.
|
|
1009
|
+
# [LEDGER 2026-09-17 @4.116.0] BUILT + unit-tested (endTurnResolver.test.ts R167). Field: PENDING (pilot-12 rerun, confirm on vs off).
|
|
1010
|
+
#CORTEX_FINISH_CONFIRM=
|
|
1011
|
+
#CORTEX_FINISH_CONFIRM_MIN_REMAINING=
|
|
1012
|
+
#CORTEX_FINISH_CONFIRM_MAX=
|
|
987
1013
|
# (no lever) 4.110.0 closes the 4.109.0 disclosures (2026-09-16): R154 image-rejection heal now also covers the STREAMING loop
|
|
988
1014
|
# (continuation re-streamed once after the stub; stream empty-retry and stream R29a synthesis wrapped like the non-streaming calls);
|
|
989
1015
|
# 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
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@nexus-cortex/cli",
|
|
3
|
-
"version": "4.
|
|
3
|
+
"version": "4.116.0",
|
|
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": "4.116.0",
|
|
23
23
|
"chalk": "^4.1.2",
|
|
24
24
|
"cli-spinners": "^2.9.0",
|
|
25
25
|
"commander": "^11.0.0",
|