@nexus-cortex/cli 4.90.2 → 4.91.1

package/.cortex/orient

@@ -38,12 +38,15 @@ for b in file xxd strings ps pgrep free pdftotext tesseract gcc make git curl; d
   if command -v "$b" >/dev/null 2>&1; then HAVE="$HAVE $b"; else MISS="$MISS $b"; fi
 done
 echo "-- tooling:${TI:- (no python/node on PATH)} | have:${HAVE:- none} | missing:${MISS:- none}"
-[ -f requirements.txt ] && echo "-- python deps: requirements.txt ($(wc -l < requirements.txt | tr -d ' ') lines)"
-[ -f pyproject.toml ] && echo "-- python: pyproject.toml present"
-[ -f Cargo.toml ] && echo "-- rust: Cargo.toml present (cargo build / cargo test)"
-if [ -f Makefile ]; then
-  echo "-- make targets --"
-  sed -n 's/^\([A-Za-z0-9_.-][A-Za-z0-9_.-]*\):.*/  make \1/p' Makefile | head -8
+# Bare-box hint (2026-09-03, operator-simplified): a task container may ship WITHOUT the language, compiler,
+# package or library the objective needs — on purpose (the agent phase is bare; internet is usually allowed).
+# State the FACTS (package manager present, whether we are root) and ONE principled directive — no command
+# cookbook: the model bootstraps correctly on its own (pro solved a bare-box torch task with only this line).
+# Prescribing exact incantations is prompt mass that misdirects; observation + intent is enough.
+if [ "${CORTEX_ORIENT_BOOTSTRAP:-0}" = "1" ] && { ! command -v python3 >/dev/null 2>&1 && ! command -v python >/dev/null 2>&1 || ! command -v cc >/dev/null 2>&1; }; then
+  PM=""; for m in apt-get apk dnf yum pacman zypper brew; do command -v "$m" >/dev/null 2>&1 && { PM="$m"; break; }; done
+  ROOT=$([ "$(id -u 2>/dev/null)" = "0" ] && echo yes || echo no)
+  echo "-- setup: this box may be missing a tool/language/library the task needs (pkg-mgr=${PM:-none}, root=$ROOT). If so, INSTALL what you need yourself following standard practice (the system package manager, or the language's own installer); install ONCE and reuse it, and prefer a fast cached installer for the language (uv for Python, bun for JS) — do not re-download a large dependency twice. Pin versions, then verify with a real run before finishing. An empty box is part of the task, not an error."
 fi
 if [ -f README.md ]; then
   echo "-- README head --"

package/.env.example

@@ -7,7 +7,7 @@
 # ║ .cortex/bench/r-*.md. K=5 CONFIG (settled 2026-09-03 @4.90.1, r-v4-validation):    ║
 # ║ ON set + CORTEX_ENDTURN_GATE=true + CORTEX_ENDTURN_REQUIREMENTS=strict +           ║
 # ║ ENABLE_WEBTOOLS=false (bench pin) + VISION_HELPER_MODEL on + TOOL_TIMEOUT_MODE=auto; ║
-# ║ MENTOR_AUTO / EFFORT_TAIL / EFFORT_PULSE dark. Pin nexus-cortex@4.90.1 (4.90.0's    ║
+# ║ MENTOR_AUTO / EFFORT_TAIL / EFFORT_PULSE dark. Pin nexus-cortex@4.91.0 (4.90.0.s    ║
 # ║ timeout-promote was inert). Both models.                                            ║
 # ╚══════════════════════════════════════════════════════════════════════════════════╝
 # Copy to .env and fill in the API keys for the providers you use. Every other value
@@ -271,6 +271,10 @@ MENTORSHIP_HELPER_MODEL=deepseek-v4-pro
 # montage of individually LABELED squares (def-a3e7920cf9): grid/crop-aware prompts beat whole-image reads; a stronger
 # vision card is the next lever once available.
 VISION_HELPER_MODEL=deepseek-v4-flash-vision-exp
+# Per-turn cap on ReadImage→vision-helper hand-offs (0 = unlimited). Past the cap ReadImage returns a
+# "consolidate your reads into ONE labeled montage / change approach" reminder instead of another vision call.
+# [LEDGER 2026-09-03 @4.91.0] ON=8 — ✅ v5 CERTIFIED: flash gcode-to-text fired vis×8 then vision_handoff_capped×2 (v4 was 14 uncapped) — cap bounds the runaway (gcode still fails: it is GEOMETRIC not OCR, vision is the wrong approach there). v4 gcode-to-text: 14 (flash) / 34 (pro) slice reads burned the whole task budget without converging (def-fcb719427f); chess flash passed with 6 reads. Cap event kind: vision_handoff_capped. Measure at k=5 (gcode budget_frac, chess flips).
+VISION_HANDOFF_MAX=8
 # Periodic mentorship review every N turns
 MENTORSHIP_TURN_BASED_ENABLED=false
 # Turns between periodic reviews (1-50)
@@ -344,7 +348,7 @@ TOOL_BUDGET_SOFT=400
 # deadline in interactive ones.
 # [LEDGER 2026-09-02 @4.90.0] ON=120000 — p3 timeout audit (r-p3): the 120s kill fired 42× across 14 task-runs and RESCUED NONE (train-fasttext busy-wait driver, long builds); every p3 timeout was Harbor's budget, not ours. Kept at 120s because TOOL_TIMEOUT_MODE=auto promotes instead of kills in headless (item 8). v4 audit: pro/train-fasttext = the busy-wait driver again (249 bash, 22 cancels) and 4.90.0's promote was INERT (outer-abort race, fixed 4.90.1) → train-fasttext is the 4.90.1 re-test task.
 TOOL_TIMEOUT_MS=120000
-# [LEDGER 2026-09-03 @4.90.1] ON=auto — 🔴 4.90.0 was INERT: the orchestrator's outer abort raced ShellTool's deadline and always won (v4 pro/train-fasttext: 22 cancelled, 0 promoted). 4.90.1: outer cap = TOOL_TIMEOUT_MS+30s, ShellTool default follows TOOL_TIMEOUT_MS; LIVE-VERIFIED (5s deadline, 9s command → tool_promoted event, model read the background output). Re-test task: train-fasttext. PROMOTE-AT-DEADLINE: when a Bash call exceeds TOOL_TIMEOUT_MS in a
+# [LEDGER 2026-09-03 @4.91.0] ON=auto — ✅ v5 CERTIFIED FIRING on the real bench (tool_promoted: flash 2 / pro 2, on train-fasttext + dna-insert). 4.90.0 was INERT: the orchestrator's outer abort raced ShellTool's deadline and always won (v4 pro/train-fasttext: 22 cancelled, 0 promoted). 4.90.1: outer cap = TOOL_TIMEOUT_MS+30s, ShellTool default follows TOOL_TIMEOUT_MS; LIVE-VERIFIED (5s deadline, 9s command → tool_promoted event, model read the background output). Re-test task: train-fasttext. PROMOTE-AT-DEADLINE: when a Bash call exceeds TOOL_TIMEOUT_MS in a
 # headless/auto-approve session, the still-running command is moved to a background shell (bash_id) and the tool
 # returns the output so far instead of killing it; interactive sessions keep the kill. Evidence (c3/p3 trajectories):
 # the 120s kill fired 42x across 14 task-runs (19 legitimate scripts, 12 wait loops, 5 builds/trainings) and rescued
@@ -447,7 +451,7 @@ ROUTER_MIN_SAMPLES=3
 
 # Mandatory EndTurn pre-delivery self-audit + Stage 2/3 verifiers. Default OFF; ON =
 # graded cortex-channel training records (the tool is hidden when off).
-# [LEDGER 2026-09-03 @4.90.2] DARK/PENDING → **RECOMMENDED ON for k=5 (with REQUIREMENTS=strict)** — COST (v4 pass mining + doctrine-mine): every pass paid 4-8 EndTurn round-trips, the biggest share = Stage-2 CITATION rejects (17/43 doctrine findings; the model never re-ran a command for a fresh verbatim line) → 4.90.2 nudge teaches per-turn grounding + re-run; expect controls' +25-35% turn tax to drop — measure at k=5. — v4 (n=1, @4.90.0): gate engaged heavily under strict (flash gate_req=22/cite=13, pro 17/4), controls bn-fit+sqlite held on BOTH models, pro flips vs p3: dna-insert, pytorch-model-cli, cancel-async (n=1 candidates). Prior 3 cells: 4.71 fp 11→1 · fd +2/5 · c3 (n=2, r-c3-candidate-config) code-from-image FLIP 2/2 (first flash-family pass ever; Stage-4 requirement rejections, no mentor) + dna-insert 1/2; 0 clean regressions outside its LIMIT (accepts a re-attested wrong artifact: pytorch-model-cli r2, dna-insert fd). Cost: attestation turns. Operator decision pending. PRO (r-p3, n=1): controls 3/3 held with NO attestation tax (bn-fit 53→30 turns), 0 regressions, 0 paralysis; 0/13 flips on pro's hard core (budget timeouts while working). → k=5 config for BOTH models: guards + GATE+REQ + ENABLE_WEBTOOLS=false, mentor/tail off.
+# [LEDGER 2026-09-03 @4.91.0] DARK/PENDING → **RECOMMENDED ON for k=5 (with REQUIREMENTS=strict)** — 4.91.0: gates now run on the STREAMING path too (were sendMessage-only; one shared endTurnGates.ts, live-proven on stream:true) and Stage-2 grounding accepts text the model WROTE this turn (Write/Edit content) — the false 'not grounded' rejections on authored files are gone. COST (v4 pass mining + doctrine-mine): every pass paid 4-8 EndTurn round-trips, the biggest share = Stage-2 CITATION rejects (17/43 doctrine findings; the model never re-ran a command for a fresh verbatim line) → 4.90.2 nudge teaches per-turn grounding + re-run; expect controls' +25-35% turn tax to drop — measure at k=5. — v4 (n=1, @4.90.0): gate engaged heavily under strict (flash gate_req=22/cite=13, pro 17/4), controls bn-fit+sqlite held on BOTH models, pro flips vs p3: dna-insert, pytorch-model-cli, cancel-async (n=1 candidates). Prior 3 cells: 4.71 fp 11→1 · fd +2/5 · c3 (n=2, r-c3-candidate-config) code-from-image FLIP 2/2 (first flash-family pass ever; Stage-4 requirement rejections, no mentor) + dna-insert 1/2; 0 clean regressions outside its LIMIT (accepts a re-attested wrong artifact: pytorch-model-cli r2, dna-insert fd). Cost: attestation turns. Operator decision pending. PRO (r-p3, n=1): controls 3/3 held with NO attestation tax (bn-fit 53→30 turns), 0 regressions, 0 paralysis; 0/13 flips on pro's hard core (budget timeouts while working). → k=5 config for BOTH models: guards + GATE+REQ + ENABLE_WEBTOOLS=false, mentor/tail off.
 CORTEX_ENDTURN_GATE=false
 # Stage 4 (4.70.0, requires the gate ON): task-requirements attestation —
 # enumerate each stated requirement with what satisfies it + how it was
@@ -458,7 +462,7 @@ CORTEX_ENDTURN_GATE=false
 # (a claim with no matching tool output is rejected). Motivation: 4 pro fails
 # (cancel-async-tasks, dna-assembly, dna-insert, pytorch-model-cli) were 85-95% complete with
 # TRUE attestations verified against the model's own tests, not the task's exact constraints.
-# [LEDGER 2026-09-03 @4.90.1] DARK/PENDING → `strict` RECOMMENDED for k=5 with the gate. v4 cell (n=1): strict rejects fired heavily (flash gate_req=22, pro=17), 0 control regressions. 🔴 4.90.0 strict CRASHED on EndTurn({}) (null.filter ×4, flash/dna-insert) and rejected 11 honest condensations as paraphrases (protein-assembly) → 4.90.1: null-guarded; verbatim = 24-char window OR ≥70% content tokens; nudge shows a pasted-output example. Needs GATE.
+# [LEDGER 2026-09-03 @4.91.0] DARK/PENDING → `strict` RECOMMENDED for k=5 with the gate. 4.91.0: verified_how also grounds on a Bash command that RAN this turn (12-char windows) so the recommended `$ cmd → output` form passes; Stage-1 reminder names `requirements`. v4 cell (n=1): strict rejects fired heavily (flash gate_req=22, pro=17), 0 control regressions. 🔴 4.90.0 strict CRASHED on EndTurn({}) (null.filter ×4, flash/dna-insert) and rejected 11 honest condensations as paraphrases (protein-assembly) → 4.90.1: null-guarded; verbatim = 24-char window OR ≥70% content tokens; nudge shows a pasted-output example. Needs GATE.
 #CORTEX_ENDTURN_REQUIREMENTS=false
 
 # ============================================
@@ -741,7 +745,7 @@ CORTEX_POLL_GUARD=true
 # 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).
-# [LEDGER 2026-09-02 @4.89.0] ON — guard stack Stage-5 (transplant/solution-query audit + sources attestation; justify-don't-block). Constant-on in every bench arm incl. controls. Fired 'unattested web use 12/12' on protein-assembly (fd) → one of 3 web-tool taxes behind ENABLE_WEBTOOLS.
+# [LEDGER 2026-09-03 @4.91.0] ON — guard stack Stage-5 (transplant/solution-query audit + sources attestation; justify-don't-block); since 4.91.0 also evaluated on the streaming path. Constant-on in every bench arm incl. controls. Fired 'unattested web use 12/12' on protein-assembly (fd) → one of 3 web-tool taxes behind ENABLE_WEBTOOLS.
 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-
@@ -754,6 +758,16 @@ CORTEX_SURRENDER_NUDGE=true
 # N-in-window → one diversify nudge; 2N → break. Default off; bench/serving arm it.
 # [LEDGER 2026-09-02 @4.89.0] ON — guard stack; the retry-loop ladder (retry_loop = 65-74% of fails pre-guards). Code defaults NEARDUP_NUDGE_AT=12 (8 regressed rstan-class grinds) / NEARDUP_WINDOW=30 (break rung unreachable at 20).
 CORTEX_NEARDUP_BREAKER=true
+# Slice-reader nudge: after the 3rd bash slice-read (sed -n N,Mp / head -n / tail -n) of the SAME file in a session,
+# 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
+# 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
+# directive. The factual tooling line is always on; this flag adds the directive.
+# [LEDGER 2026-09-03 @4.91.1] DARK (default 0) — ships dark, A/B-able (def-60a1dfc55a); do NOT bake into the k=5 pin.
+#CORTEX_ORIENT_BOOTSTRAP=0
 # [LEDGER 2026-09-02 @4.89.0] code default 30 (4.88.0) — 20 made the break rung (2N=24) unreachable; preserves 40%/80% density semantics.
 #NEARDUP_WINDOW=30
 # [LEDGER 2026-09-02 @4.89.0] code default 12 (4.88.0) — 8 misfired on persistence-wins grinds (rstan-to-pystan regressed both arms).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.90.2",
+  "version": "4.91.1",
   "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": "4.90.2",
+    "@nexus-cortex/core": "4.91.1",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",