@nexus-cortex/cli 4.97.0 → 4.99.0

package/.env.defaults

@@ -135,8 +135,16 @@ CLAUDE_CODE_OAUTH_TOKEN=
 # Optimal TB2 apprentice tier — pairs with the pro MENTORSHIP_HELPER_MODEL (stronger mentor).
 # [LEDGER 2026-09-02 @4.89.0] ON — flash is the apprentice (cheap, ties/edges frontier under the narrow door); pro = leaderboard candidate (TB2.1 n=1 78.7% guardless, ~82% projected guarded).
 DEFAULT_MODEL_ID=deepseek-v4-flash
-# Cheaper model for context compaction & mentorship
-HELPER_MODEL_ID=deepseek-v4-flash
+# Cheaper model for context compaction & auxiliary helper calls (web-fetch summary, error guidance,
+# the ReadImage/describeImage vision hand-off). VISION-CAPABLE default (2026-09-09): flash-vision-exp
+# is SAME cost ($0.14/$0.28), near-identical text (bench-arm parity flash vs flash-vision), + adds
+# vision so ONE helper card also serves the image hand-off (VISION_HELPER_MODEL can collapse into it).
+# 🔴 LATENT: compaction + tool-result summarization currently FLATTEN image blocks to text before the
+# helper (handleToolResultOverflow JSON.stringify's content; renderBlock has no image case → drops it),
+# so vision only helps the explicit describeImage path TODAY. Realizing it for tool-results/compaction
+# needs a follow-up that emits image parts (HelperMiddlewareAdapter already supports `image` blocks).
+# Mentor roles override this via MENTORSHIP_HELPER_MODEL below (stay deepseek-v4-pro).
+HELPER_MODEL_ID=deepseek-v4-flash-vision-exp
 
 # Model that backs WebSearch / WebFetch tools. Provider auto-detected from ID prefix.
 # When unset, auto-picks based on available API keys (Gemini > Anthropic > XAI),
@@ -267,6 +275,10 @@ CORTEX_EFFORT_TAIL=false
 #   tokens). PRO low≈medium too close (pe-lo/pe-md torn down at egress-rot). ⇒ flash-low confirmed at
 #   n=1 → card reasoning.effortByRole.action bake pending k=5; pro-track k=5 (low vs med, mentors@max)
 #   STILL OWED. Do NOT ship-on: n=1, k=5-gated. Stays dark/UNSET in production.
+# 🔴 LADDER FACT (DS API docs, 2026-09-09): reasoning_effort = {low, high, max} ONLY. 'medium' is
+#   accepted but COERCED → 'high' server-side, so the card default 'medium' effectively runs HIGH.
+#   ⇒ the flash-low verdict was low-vs-HIGH (not low-vs-medium): ~30% cheaper at pass-rate WASH.
+#   Applies to the ACTION model here; the mentor roles run 'max' (top), the helper middleware runs 'none'.
 #CORTEX_ACTION_EFFORT=
 # Trigger helper-model review on tool errors (only applies when mentorship is enabled)
 MENTORSHIP_TRIGGER_ON_ERROR=false
@@ -627,6 +639,11 @@ CORTEX_DECISIONS_MAX_BYTES=2097152
 # agent/the user has since changed on disk). Lets two agents share one working tree safely.
 # Default ON; set "false" to disable.
 CORTEX_GIT_CONTEXT=true
+# Turn-0 "Available Slash Commands" harness-note: lists the built-in /commands (grouped by category)
+# so the model can SUGGEST them to a user when relevant. Interactive/workspace feature — there is no
+# user in a headless/bench task, so it is pointless prompt mass there. Default ON; set "false" to drop
+# it (the bench COMMON sets it false). [LEDGER 2026-09-09] added — headless/bench frame hygiene.
+CORTEX_SLASH_COMMAND_HINT=true
 
 # ============================================
 # ORCHESTRATOR MODE
@@ -909,6 +926,16 @@ CORTEX_NEARDUP_BREAKER=true
 # append a one-line reminder to read the file once with Read (offset/limit) instead. Event kind: slice_read.
 # [LEDGER 2026-09-03 @4.91.0] ON — ✅ v5 CERTIFIED: slice_read fired (flash 3 / pro 4, on gcode/make-doom/train-fasttext/dna). Doctrine gap flagged 08-29 (A′ doctrine-mine) and recurring in v4 make-doom on BOTH models (5 sed slices of /app/vm.js each); the Bash description's Read-preference line alone does not hold under the bash-edit frame. Post-tool reminder = no turn-1 prompt mass.
 CORTEX_SLICE_NUDGE=true
+# HB-SLICE-BLOCK — coercive escalation of the slice-nudge (dark). Full-sample mining (k5 @4.91.1, 66 nudge-fires)
+# proved the soft slice-nudge is IGNORED ~80% of re-tested cases (93% of ignored files are NEVER Read); harm
+# concentrates in a 39% deep-grinder tail (up to 23 extra slices of one file). So after CORTEX_SLICE_BLOCK_AT
+# slices of a STATIC/source file, BLOCK further slice-reads of it (force Read via an append-only redirect,
+# cache-safe), bounded to CORTEX_SLICE_BLOCK_MAX/file; append-mostly logs (re-tailing) are EXEMPT. Banks slice_block.
+# [LEDGER 2026-09-09 @unreleased] DARK/PENDING — built + 11 unit tests green; A/B on the slice-heavy source pop
+#   (gcode/make-doom/dna-*/fix-ocaml-gc/build-pmars/make-mips) owed. Spec: docs/HB-SLICE-BLOCK-SPEC.md.
+#CORTEX_SLICE_BLOCK=
+#CORTEX_SLICE_BLOCK_AT=5
+#CORTEX_SLICE_BLOCK_MAX=2
 # Orient bootstrap directive: when a bare box lacks the language/compiler/library the task needs, orient prints one
 # principled "install what you need + install once + fast cached installer" line. GATED because it is UNPROVEN —
 # the one bare-box pass we have (tp torch-tensor, 4.91.0) happened with ONLY orient's factual tooling line, no

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.97.0",
+  "version": "4.99.0",
   "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": "4.97.0",
+    "@nexus-cortex/core": "4.99.0",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",