@nexus-cortex/cli 4.104.0 → 4.106.0

package/.env.defaults

@@ -308,6 +308,7 @@ MENTORSHIP_CUSTOM_KEYWORDS=
 #   lift plan / resolver verdict / deadline-exit / loop-exit / consult in every cell to date was a NON-thinking call. From
 #   4.103.0 the mentor's *_EFFORT (max) is sent as reasoning_effort. cell-m is the first cell with a thinking mentor.
 MENTORSHIP_HELPER_MODEL=deepseek-flash
+# [LEDGER 2026-09-10 @4.105.0] cell-m pilot thinking-OFF: pro-none 1/4 vs flash-none 2/4 (n=4, noise), both delivered ~5 KB plans + parsed verdicts in 5-9 s. STATUS: deepseek-flash (default) for the k=5 — V4 Pro routes to flash 2026-09-14 04:00 UTC anyway.
 # ── MENTOR ROLE (2026-09-10, training/mentorRole.ts) — the bounded single-shot judges/planners are a ROLE, distinct from
 #    the HELPER role (HELPER_MODEL_ID: compaction/summaries/vision, thinking OFF). Model = MENTORSHIP_HELPER_MODEL above;
 #    per-surface effort/budget/timeout = CORTEX_LIFT_PLAN_* / CORTEX_ENDTURN_RESOLVER_* / CORTEX_DEADLINE_EXIT_MENTOR_* /
@@ -321,12 +322,31 @@ MENTORSHIP_HELPER_MODEL=deepseek-flash
 #   +17pp, cell-d-k3 judges) was measured with thinking OFF on the wire despite the "@max" configs (HB-MENTOR-THINKING); the
 #   plans were real and non-empty even so. `none` reproduces that baseline. cell-m A/Bs {pro, deepseek-flash} × {on, none}.
 #CORTEX_MENTOR_REASONING=on
+# [LEDGER 2026-09-10 @4.105.0] cell-m pilot (8 arms, n=4): `on` is BROKEN for DeepSeek planners as shipped — reasoning shares max_tokens (4000), so pro@low/high/max returned 0/10 lift plans + 1/8 resolver verdicts (blank after 50-75 s) and flash 3/10 + 2/9; every blank verdict fail-opened to MEETS. `none` = 8/8 plans, 12/12 verdicts, 5-9 s. STATUS: keep `none` (k=5 COMMON) until HB-MENTOR-BUDGET ships (max_tokens = content budget + reasoning allowance; finish_reason=length → retry thinking-off). Ledger .cortex/bench/r-cell-m-2026-09-10.md
 #   CORTEX_MENTOR_CONSULT_REASONING — on|none. The AskForAdvice consult hint (400-token budget). Default none: the
 #   08-30 measurement — thinking-on hints came back BLANK (reasoning ate the budget); the m88 results were thinking-off.
 # [LEDGER 2026-09-10 @4.104.0] none (default) — unmeasured ON; opt in per cell.
 #CORTEX_MENTOR_CONSULT_REASONING=none
+#   CORTEX_MENTOR_EFFORT — low|medium|high|max. ONE effort for every planner surface (the mentor-effort A/B lever); a
+#   surface's own *_EFFORT (CORTEX_LIFT_PLAN_EFFORT etc.), when explicitly set, wins over it. Empty = per-surface (max).
+# [LEDGER 2026-09-10 @4.105.0] unset — cell-m A/Bs {pro, deepseek-flash} × {low, high, max} (+ thinking-off baselines).
+#CORTEX_MENTOR_EFFORT=
+# [LEDGER 2026-09-10 @4.105.0] cell-m pilot: low/high/max UNMEASURABLE — the thinking-on calls came back empty (see CORTEX_MENTOR_REASONING). Only flash@low ever delivered (1/4 plans, 2/3 verdicts). Re-test after HB-MENTOR-BUDGET.
+#   CORTEX_ASK_FOR_ADVICE — true|false. Include the model-initiated AskForAdvice consult tool while mentorship is on.
+#   =false drops it (and the forced-consult path) so a mentor effort/model A/B carries no consult confound.
+# [LEDGER 2026-09-10 @4.105.0] true (default) — the consult was measured thinking-off with weak voluntary heed (v1 0/6,
+#   m88 auto-consult neutral); cells set false unless the consult is the thing under test.
+#CORTEX_ASK_FOR_ADVICE=true
 #   CORTEX_MENTOR_TEMPERATURE — optional sampling temperature for mentor calls (0-2); empty = adapter default 0.7.
 #CORTEX_MENTOR_TEMPERATURE=
+#   CORTEX_MENTOR_REASONING_ALLOWANCE — integer tokens. HB-MENTOR-BUDGET (4.106.0): DeepSeek counts reasoning tokens INSIDE
+#   max_tokens, so a thinking-on mentor call sends max_tokens = content budget (e.g. 4000) + this allowance; empty = the
+#   per-effort table low 4000 / medium 8000 / high 12000 / max 24000 (capped by the card's outputTokens). A thinking-on call
+#   that still returns EMPTY content is re-issued ONCE thinking-off and the event banks truncated/retriedThinkingOff.
+# [LEDGER 2026-09-10 @4.106.0] BUILT from the cell-m pilot (0/10 pro lift plans, 1/8 verdicts at the 4000 cap; direct API:
+#   completion_tokens 2045 = 1641 reasoning + ~400 content). UNTESTED on the bench — the flash-none vs flash-high re-pilot
+#   (K=2) is the efficacy test; until then CORTEX_MENTOR_REASONING=none stays the k=5 COMMON.
+#CORTEX_MENTOR_REASONING_ALLOWANCE=
 
 # [LEDGER 2026-09-02 @4.90.0] ON — the VISION HAND-OFF (operator design): text-only primaries keep the ReadImage
 # tool; the orchestrator sends the image + the caller's `prompt` to this vision card THROUGH THE HELPER MIDDLEWARE

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.104.0",
+  "version": "4.106.0",
   "description": "Nexus Cortex CLI - Terminal interface for multi-provider LLM orchestration",
   "main": "dist/index.js",
   "type": "module",
@@ -19,7 +19,7 @@
     "prepack": "node ../../scripts/copy-pkg-cortex-scaffold.mjs"
   },
   "dependencies": {
-    "@nexus-cortex/core": "4.104.0",
+    "@nexus-cortex/core": "4.106.0",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",