@nexus-cortex/cli 4.123.3 → 4.124.0
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 +16 -0
- package/package.json +2 -2
package/.env.defaults
CHANGED
|
@@ -1150,6 +1150,22 @@ CORTEX_ENDTURN_GATE=true
|
|
|
1150
1150
|
# after the multi-line command text, so checksPassed read 0 → inconclusive everywhere. R176c locates the verdict by marker. Cell r176c relaunched.
|
|
1151
1151
|
#CORTEX_JUDGE_INDEPENDENT_DERIVATION=
|
|
1152
1152
|
#CORTEX_JUDGE_INDEPENDENT_DERIVATION_TOL=
|
|
1153
|
+
# CORTEX_FRAME / _CHOOSER / _CANDIDATES / _WAIT_CAP_S / _SCREEN_LINES — R179 HB-TERMINUS-FRAME + R178 typed chooser (4.124.0, 2026-09-21; design
|
|
1154
|
+
# docs/R179_TERMINUS_FRAME_PORT_DESIGN.md, docs/R178_TYPED_CHOOSER_DESIGN.md). The one variable never varied between our 18% and Terminus 2's 26.8
|
|
1155
|
+
# on TB4.0 flash is the FRAME. `CORTEX_FRAME=terminus`: the model gets ONE tool, FrameAction (+ EndTurn), works one tmux pane; each turn returns
|
|
1156
|
+
# the screen (ANSI-stripped, last _SCREEN_LINES), a STATE card computed in code (turn, commands, last rc from a PROMPT_COMMAND hook, budget,
|
|
1157
|
+
# repeats, digest) and the harness templates (WAIT / INTERRUPT / SHOW MORE / RUN THE TASK'S TEST / RE-READ / FINISH). The prefix stays cached
|
|
1158
|
+
# (one small tool schema; the contract is appended to the system prompt on turn 0 and pinned); only the tool_result changes. `_CHOOSER=jev`: a typed
|
|
1159
|
+
# reader (Jev) sees the raw screen + state + the writer's candidates — never the judge (E0: it echoes it) — picks the action (>= 0.3), refuses
|
|
1160
|
+
# unsafe (>= 0.7), restricts repeats to templates, flags an unaddressed on-screen error (the writer then gets the full screen once); fail-open to
|
|
1161
|
+
# candidate 1. Every turn banks a `frame_turn` event (candidates, pick, probabilities, provenance, rc, wait) = Lens A rows on agent actions.
|
|
1162
|
+
# [LEDGER 2026-09-21 @4.124.0] BUILT + 23 unit tests (frames/); LOCAL SMOKE PASSED (deepseek-flash, toy task: 3 frame turns — orient, printf, cat/ls/wc — file correct,
|
|
1163
|
+
# EndTurn gate rejected once then accepted, 37 s, 3.5K tokens; frame_turn events banked with provenance); E1 = frame vs control on g1-35 (~$40); E2 = chooser on (~$40).
|
|
1164
|
+
#CORTEX_FRAME=
|
|
1165
|
+
#CORTEX_FRAME_CHOOSER=
|
|
1166
|
+
#CORTEX_FRAME_CANDIDATES=
|
|
1167
|
+
#CORTEX_FRAME_WAIT_CAP_S=
|
|
1168
|
+
#CORTEX_FRAME_SCREEN_LINES=
|
|
1153
1169
|
# (no lever) R169 HB-NEARDUP-SCRATCH-STEM — REFUTED before shipping (2026-09-17, pilot-12 trajectory replay). The distiller's 16
|
|
1154
1170
|
# "repeated-identical-retry" candidates were re-read: the two stuck sessions (coq-block-bound base arm: `cat > /tmp/tN.v <<EOF` with a
|
|
1155
1171
|
# 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": "4.124.0",
|
|
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": "4.124.0",
|
|
23
23
|
"chalk": "^4.1.2",
|
|
24
24
|
"cli-spinners": "^2.9.0",
|
|
25
25
|
"commander": "^11.0.0",
|