@nexus-cortex/cli 4.82.0 → 4.83.0

package/.env.example

@@ -109,7 +109,8 @@ CLAUDE_CODE_OAUTH_TOKEN=
 # ============================================
 
 # Default model for new sessions (any registry ID or alias — `cortex models list`)
-DEFAULT_MODEL_ID=deepseek-v4-pro
+# Optimal TB2 apprentice tier — pairs with the pro MENTORSHIP_HELPER_MODEL (stronger mentor).
+DEFAULT_MODEL_ID=deepseek-v4-flash
 # Cheaper model for context compaction & mentorship
 HELPER_MODEL_ID=deepseek-v4-flash
 
@@ -149,8 +150,14 @@ PROJECT_PATH=
 # REACTIVE MENTORSHIP (AI-to-AI self-improvement)
 # ============================================
 
-# Master switch for the mentorship system
-MENTORSHIP_ENABLED=false
+# Master switch for the mentorship system. ON = a stronger MENTORSHIP_HELPER_MODEL mentors
+# the primary model (AskForAdvice hints on thrash). Only meaningful when the primary
+# (DEFAULT_MODEL_ID) is WEAKER than the helper — a same-tier pair adds nothing.
+MENTORSHIP_ENABLED=true
+# Forced-tool_choice backstop (AskForAdvice v2): on HIGH-confidence thrash, FORCE the model to
+# call AskForAdvice for one turn. Voluntary heed is ~0 (0/47 lifted transcripts), so forcing is
+# what actually makes the mentor fire. OFF by default — the v2 forcing path is not yet TB2-validated.
+CORTEX_MENTOR_FORCE=false
 # Trigger helper-model review on tool errors (only applies when mentorship is enabled)
 MENTORSHIP_TRIGGER_ON_ERROR=false
 # Minimum error severity to trigger. Options: low, medium, high
@@ -160,10 +167,13 @@ MENTORSHIP_KEYWORDS_ENABLED=false
 # Additional trigger keywords (comma-separated, e.g. @help,@stuck)
 MENTORSHIP_CUSTOM_KEYWORDS=
 # Model used for mentorship guidance (overrides HELPER_MODEL_ID).
-# Default = deepseek-v4-flash for SINGLE-PROVIDER congruence: the shipped harness
-# (and the TB2 bench container) reuses the main DeepSeek key — no 2nd API key needed.
+# MUST be a STRONGER model than the primary/apprentice model: the mentor gives HINTS the
+# weaker model cannot produce on its own (AskForAdvice), so a same-tier helper adds nothing.
+# Default = deepseek-v4-pro — still SINGLE-PROVIDER (reuses the main DeepSeek key, no 2nd API
+# key needed), just the stronger DeepSeek tier. Pair with DEFAULT_MODEL_ID=deepseek-v4-flash
+# (apprentice) so the mentor is genuinely stronger on the task.
 # (For image/vision background tasks, deepseek-v4-flash-vision-exp is the vision-capable option.)
-MENTORSHIP_HELPER_MODEL=deepseek-v4-flash
+MENTORSHIP_HELPER_MODEL=deepseek-v4-pro
 # Periodic mentorship review every N turns
 MENTORSHIP_TURN_BASED_ENABLED=false
 # Turns between periodic reviews (1-50)
@@ -218,7 +228,7 @@ MEMORY_ARCHIVE_MAX_BYTES=10000
 # Maximum tool executions per turn
 MAX_TOOL_ITERATIONS=1000
 # Stop the turn after this many consecutive all-error iterations
-MAX_CONSECUTIVE_ERRORS=3
+MAX_CONSECUTIVE_ERRORS=6
 # Soft per-turn tool-call budget (R29b brake: escalating reminders, hard cap at 2x)
 # 0 disables budget pressure entirely (R64)
 TOOL_BUDGET_SOFT=400
@@ -234,11 +244,11 @@ MAX_LOOP_REPETITIONS=5
 # Bench/server profiles: wrap bash commands with `set -o pipefail` so
 # `failing-cmd | tail` classifies as a failure instead of masking behind the
 # pipe's exit 0. NEVER default-on (changes user command semantics).
-#CORTEX_BASH_PIPEFAIL=false
+CORTEX_BASH_PIPEFAIL=true
 # Lift the Bash $() command-substitution block entirely (sandboxed profiles,
 # e.g. bench containers — an OPERATOR decision; the check is a security
 # control). $(( )) arithmetic is never flagged regardless of this setting.
-#CORTEX_ALLOW_CMD_SUBSTITUTION=false
+CORTEX_ALLOW_CMD_SUBSTITUTION=true
 # Inaction guard (ladder's inverse, 4.70.0): one bounded "act first" retry on a
 # long actless first-turn response in a tool-capable request. Default OFF.
 #CORTEX_INACTION_NUDGE=false
@@ -275,7 +285,7 @@ MODEL_ROUTER_ENABLED=false
 # Routing strategy: auto (classify the prompt) | matrix-only (require explicit task type)
 MODEL_ROUTER_STRATEGY=auto
 # Record turn metrics to .cortex/router-matrix.jsonl (independent of routing being enabled)
-MODEL_ROUTER_RECORD=true
+MODEL_ROUTER_RECORD=false
 # Models the router must NEVER auto-select (cost/policy bans), comma-separated.
 # A trailing '*' is a prefix wildcard: 'grok*' excludes EVERY xAI model (present and
 # future) so exploration can never route a sub-agent to a grok model — honors the
@@ -469,7 +479,7 @@ MENTORSHIP_ACTIVE_DISCOVERY=false
 # ============================================
 # Env override for the model card's anchorProfile (deepseek cards default to
 # bash-edit). Values: lean | bash-only | bash-plus | bash-edit | none.
-#CORTEX_TOOL_ANCHOR=bash-edit
+CORTEX_TOOL_ANCHOR=bash-edit
 # ── Vision / image-path bridge (item 7) ──
 # Turns an image stays in the request context before being stubbed out.
 # MEASURED: an image ANYWHERE in a vision-exp request disables cache reads for
@@ -530,7 +540,7 @@ MENTORSHIP_ACTIVE_DISCOVERY=false
 #CORTEX_SUBAGENT_TEMPERATURE=
 # Fetch timeouts (ms) for bench runners / client HTTP.
 #CORTEX_BENCH_FETCH_TIMEOUT_MS=
-#CORTEX_CLIENT_FETCH_TIMEOUT_MS=
+CORTEX_CLIENT_FETCH_TIMEOUT_MS=3600000
 # P0 compliance gate: allows sk-ant-oat01 subscription tokens on the raw
 # Messages path ONLY with Anthropic program approval. Leave unset otherwise.
 #CORTEX_SUBSCRIPTION_AUTH_APPROVED=false
@@ -555,25 +565,29 @@ MENTORSHIP_ACTIVE_DISCOVERY=false
 # Item 12 — task-integrity guard (anti-reward-hacking; TB2.1 bench + serving profiles).
 # Appends one static line to the system prompt (survives boot-minimal, prefix-stable):
 # outputs must derive from executed work — never retrieved/recited solutions.
-#CORTEX_TASK_INTEGRITY=true
+CORTEX_TASK_INTEGRITY=true
 # Poll guard (busy-wait class): one nudge after N consecutive identical SUCCEEDING
 # calls (run3 deficiency finding). Default off; arm in bench/serving profiles.
-#CORTEX_POLL_GUARD=true
+CORTEX_POLL_GUARD=true
 #POLL_REMIND_AT=4
 # EndTurn Stage-5 integrity verifier (item 12 layer 4): mechanical checks at the
 # gate — web-content transplant + solution-shaped queries (AUDIT-ONLY events when
 # a sources attestation is present: justify-don't-block) + mandatory show-your-work
 # `sources` attestation whenever web tools were used this turn (the one rejecting
 # check; bounded nudges, fallback-accept).
-#CORTEX_ENDTURN_INTEGRITY=true
+CORTEX_ENDTURN_INTEGRITY=true
 # Item 13b — surrender guard: one "execute your plan" nudge when a tool-using turn
 # ends by ENUMERATING remaining steps instead of doing them (the honest-premature-
 # surrender class). Default off; bench/serving profiles arm it.
-#CORTEX_SURRENDER_NUDGE=true
+CORTEX_SURRENDER_NUDGE=true
 # Item 14b — windowed near-dup breaker: outcome-agnostic sliding-window counter over
 # the normalized approach hash (catches varied-param polling invisible to the exact
 # tracker AND the poll guard — observed x65 near-identical calls, max 4 consecutive).
 # N-in-window → one diversify nudge; 2N → break. Default off; bench/serving arm it.
-#CORTEX_NEARDUP_BREAKER=true
+CORTEX_NEARDUP_BREAKER=true
 #NEARDUP_WINDOW=20
 #NEARDUP_NUDGE_AT=8
+
+
+# --- OPTIMAL LIFT CONFIG (appended) ---
+CORTEX_IDLE_TIMEOUT=120

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.82.0",
+  "version": "4.83.0",
   "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": "4.82.0",
+    "@nexus-cortex/core": "4.83.0",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",