@nexus-cortex/cli 4.124.39 → 4.124.40
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 +20 -0
- package/package.json +2 -2
package/.env.defaults
CHANGED
|
@@ -993,6 +993,16 @@ CORTEX_ENDTURN_GATE=true
|
|
|
993
993
|
# server + adapter sibling survive a matching pattern, killall spares the sibling, pgrep hides the harness, the c21ba command shape through
|
|
994
994
|
# the real Bash tool); ShellTool/BashOutput/KillShell suites unchanged (145 tests).
|
|
995
995
|
#CORTEX_KILL_GUARD=
|
|
996
|
+
# CORTEX_PID1_GUARD — R209 HB-CONTAINER-PID1 (DARK, 2026-10-01). c23gb r1 exit 137: the agent SIGKILLed `supervisord` with os.kill inside
|
|
997
|
+
# a Python script (no shell kill guard can see that); PID 1 was /app/entrypoint.sh doing `wait $supervisord_pid`, so PID 1 exited, the
|
|
998
|
+
# container stopped and the harness was SIGKILLed. on: at the first tool_result boundary (the boot observation, normally orient's output;
|
|
999
|
+
# independent of the tool anchor) the harness reads /proc/1/cmdline and the direct children of PID 1 (/proc/*/stat ppid == 1, the harness
|
|
1000
|
+
# and its ancestors excluded, max 3) and, when PID 1 is not the harness, appends ONE system-reminder: "Container init: PID 1 is `<cmd>`; it
|
|
1001
|
+
# supervises `<child>` (pid N). Killing pid N (or PID 1) stops the container and ends your session — restart services through their
|
|
1002
|
+
# supervisor (e.g. `supervisorctl restart <name>`) instead." Linux-only, one /proc pass, fail-safe (any read error → no note). One-shot
|
|
1003
|
+
# per orchestrator. Event pid1_guard {noted, pid1Cmd, children, chars} when the note is added. off: nothing read, nothing added.
|
|
1004
|
+
# [LEDGER 2026-10-01 @4.124.40] DARK — BUILT + unit-tested (pid1Guard.test.ts: fake /proc builder cases). NO bench arm yet.
|
|
1005
|
+
#CORTEX_PID1_GUARD=
|
|
996
1006
|
# (no lever) R154 HB-IMAGE-REJECTION-HEAL (4.109.0, 2026-09-16): retro-console-soc generated a 128x128 8-bit GRAYSCALE PNG, called
|
|
997
1007
|
# ReadImage, and DeepSeek answered the next continuation with `400 .messages[290].image[0]: You have uploaded an unsupported image`;
|
|
998
1008
|
# the exception escaped after the tool batch, the already-executed guard left the loop, and the R29a synthesis failed on the same block —
|
|
@@ -1087,6 +1097,16 @@ CORTEX_ENDTURN_GATE=true
|
|
|
1087
1097
|
# hold a finish. Event field namedInconclusive.
|
|
1088
1098
|
#CORTEX_JUDGE_VETO=
|
|
1089
1099
|
#CORTEX_JUDGE_EVIDENCE_MAX_VETOES=
|
|
1100
|
+
# CORTEX_VERIFY_SCALE — R208 HB-VERIFY-AT-SCALE (DARK, 2026-10-01). c23 payments-pipeline-fix 0/6: the agent applied a plausible fix,
|
|
1101
|
+
# verified it with its own small run (latency 0.2–1.9 s) and finished; the hidden tests ran ~920k records against a 5 s SLA and measured
|
|
1102
|
+
# 8–22 s. The EndTurn judge accepted the small-scale self-report. on: the judge persona (resolverSystemPrompt) carries ONE extra rubric item
|
|
1103
|
+
# (RESOLVER_SCALE_CLAUSE): does the verification reproduce the scale, volume, concurrency and timing the task's tests will use (data size,
|
|
1104
|
+
# records/requests, parallel clients, restarts, time limits) rather than a toy run? Evidence that covers only a smaller run is a GAP, and
|
|
1105
|
+
# the judge names a CHECK at the stated scale — under VETO=evidence that check is what can hold the finish (45 s check cap applies).
|
|
1106
|
+
# off: persona byte-identical. Events: verify_scale_item {surface, clauseChars, roundsUsed, meets, parsed, confidence} per adjudication;
|
|
1107
|
+
# endturn_resolver gains {verifyScale}. Needs CORTEX_ENDTURN_RESOLVER=true.
|
|
1108
|
+
# [LEDGER 2026-10-01 @4.124.40] DARK — BUILT + unit-tested (endTurnResolver.test.ts R208 cases). NO bench arm yet.
|
|
1109
|
+
#CORTEX_VERIFY_SCALE=
|
|
1090
1110
|
# CORTEX_TURN_CONTRACT — HB-TURN-CONTRACT (4.115.0, 2026-09-17; Terminus-2 disparity "suppress vs channel"). The boot-minimal door SUPPRESSES
|
|
1091
1111
|
# deliberation ("Prefer acting over deliberating"; tuned at effort low). At effort high the model fought it: tb4-flash-v3 had 58 turns in
|
|
1092
1112
|
# 23 sessions reason to the 65536 cap and emit nothing (R153). Terminus 2 CHANNELS deliberation: think freely, then every response must
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@nexus-cortex/cli",
|
|
3
|
-
"version": "4.124.
|
|
3
|
+
"version": "4.124.40",
|
|
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": "4.124.40",
|
|
23
23
|
"chalk": "^4.1.2",
|
|
24
24
|
"cli-spinners": "^2.9.0",
|
|
25
25
|
"commander": "^11.0.0",
|