@nexus-cortex/cli 4.124.59 → 4.124.60
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 +11 -0
- package/package.json +2 -2
package/.env.defaults
CHANGED
|
@@ -1044,6 +1044,17 @@ CORTEX_ENDTURN_GATE=true
|
|
|
1044
1044
|
# the disclosed max. Cards now 393,216 → an unset lever sends 393,216. Use this lever to pin a LOWER cap (e.g. 65536 to reproduce the
|
|
1045
1045
|
# old behaviour as a control, 131072 = the provider's max-effort default). Pairs with CORTEX_HTTP_TIMEOUT_MS (below).
|
|
1046
1046
|
#CORTEX_OUTPUT_CAP_TOKENS=
|
|
1047
|
+
# CORTEX_WALL_RETRY_LADDER / CORTEX_WALL_FORCE_ACTION_AT — HB-WALL-RETRY-LADDER (R241/R240, 2026-10-06, DARK). Under the 393,216 cap every
|
|
1048
|
+
# wall of the 10-05 TB4 cell was a degenerate repetition loop (40/40) and the retry re-looped from its first tokens at full price; DeepSeek has
|
|
1049
|
+
# no server-side cycle breaker in thinking mode (probed 10-06: penalties deprecated, temperature inert, stop sequences never reach
|
|
1050
|
+
# reasoning_content). LADDER = max_tokens for the retry after the n-th exhaustion wall of a turn ("65536,16384": wall 1 → 65,536, wall 2+ →
|
|
1051
|
+
# 16,384; last rung repeats; never above the request's own cap). FORCE_ACTION_AT (default 2) = from that wall on the retry carries
|
|
1052
|
+
# tool_choice:required, which the gateway turns into thinking OFF on DeepSeek → the model must emit a tool call (probed 10-06: works
|
|
1053
|
+
# mid-conversation, thinking resumes next call; costs ONE uncached prefix read). Exhaustion kinds only, never a no-tools nudge. R240 rides
|
|
1054
|
+
# along: the retry's usage is now counted in the session ledger. Events: wall_retry_ladder {wallIndex, cap, forceAction, iteration}.
|
|
1055
|
+
# [LEDGER 2026-10-06 @4.124.60] DARK — BUILT + unit/integration-tested (wallRetryLadder.test.ts, wallGuard.integration.test.ts); first arm pending.
|
|
1056
|
+
#CORTEX_WALL_RETRY_LADDER=
|
|
1057
|
+
#CORTEX_WALL_FORCE_ACTION_AT=2
|
|
1047
1058
|
# CORTEX_HTTP_TIMEOUT_MS — HTTP timeout for the NON-STREAMING chat call (2026-10-05). The openai SDK default (600 s, 2 retries) bounds the
|
|
1048
1059
|
# whole response body; a 384K-token thinking turn decodes 20–70 min, so the default would abort it and retry at double cost. Unset =
|
|
1049
1060
|
# derived from the request's max_tokens at 50 tok/s with a 600-s floor (65,536 → 1,311 s; 393,216 → 7,864 s); integer ms overrides.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@nexus-cortex/cli",
|
|
3
|
-
"version": "4.124.
|
|
3
|
+
"version": "4.124.60",
|
|
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": "4.124.60",
|
|
23
23
|
"chalk": "^4.1.2",
|
|
24
24
|
"cli-spinners": "^2.9.0",
|
|
25
25
|
"commander": "^11.0.0",
|