@nexus-cortex/cli 4.101.0 → 4.102.0

package/.env.defaults

@@ -144,7 +144,9 @@ DEFAULT_MODEL_ID=deepseek-v4-flash
 # 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
+# [LEDGER 2026-09-10 @4.102.0] deepseek-flash — DeepSeek catalog collapse: `deepseek-flash` IS V4.1 Flash (vision native, same
+#   price as the retired v4-flash / vision-exp names, which now route here anyway). One helper card, no alias risk.
+HELPER_MODEL_ID=deepseek-flash
 
 # Model that backs WebSearch / WebFetch tools. Provider auto-detected from ID prefix.
 # When unset, auto-picks based on available API keys (Gemini > Anthropic > XAI),
@@ -296,7 +298,12 @@ MENTORSHIP_CUSTOM_KEYWORDS=
 # (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.)
 # [LEDGER 2026-09-02 @4.89.0] ON=pro — NEVER a same-strength mentor: flash→flash peer = −2 engaged (m88b, confident-wrong hints lost chess+tune-mjcf); pro elder = +1 engaged (m88). For a PRO apprentice this makes pro→pro = the harmful peer config → run pro with CORTEX_MENTOR_AUTO=false.
-MENTORSHIP_HELPER_MODEL=deepseek-v4-pro
+# [LEDGER 2026-09-10 @4.102.0] deepseek-flash @max — V4 Pro is RETIRED 2026-09-14 04:00 UTC (routes to V4.1 Flash after
+#   that). DeepSeek states V4.1 Flash surpasses V4 Pro; the mentor roles (lift/resolver/deadline/loop-exit, AskForAdvice) run
+#   at effort max regardless of card. The "never a same-strength mentor" rule (m88b: v4-FLASH peer −2 engaged) was measured
+#   against V4 flash; cell-m (2026-09-10) A/Bs pro@max vs deepseek-flash@max as the mentor on the loop population before
+#   the k=5 pins it. Operator decision 2026-09-10.
+MENTORSHIP_HELPER_MODEL=deepseek-flash
 
 # [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
@@ -313,7 +320,8 @@ MENTORSHIP_HELPER_MODEL=deepseek-v4-pro
 # images misread — pro chess got a wrong whole-board transcription → bad FEN → nonsense move, while flash passed via a
 # 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
+# [LEDGER 2026-09-10 @4.102.0] deepseek-flash — V4.1 Flash is multimodal; the vision-exp name is retired and routes here.
+VISION_HELPER_MODEL=deepseek-flash
 # 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).
@@ -519,6 +527,21 @@ CORTEX_ENDTURN_RESOLVER=true
 #   failure-count/loop-block coupling (grep-verified); loop-block ships dark (no-op); distiller = tooling.
 #   ROLLBACK if k=5 shows a net regression or a high false-RETIRE rate.
 CORTEX_ENDTURN_RESOLVER_ABSTAIN=true
+#   CORTEX_JUDGE_DELTA / CORTEX_JUDGE_RUN_CHECK — HB-JUDGE-GROUNDING (2026-09-10): the done/not-done judges (EndTurn
+#   resolver, deadline exit planner) receive the ARTIFACT: a bounded workspace delta (files changed this task + heads),
+#   a FRESH environment recon at judge time (was a cached start-of-task snapshot), the LATEST tool outputs (was the
+#   oldest 4K), and — resolver only — the result of an evident check entry point (Makefile test / test.sh / pytest) run
+#   by the harness. The judge prompts already demanded an adversarial check against the task's real criteria; this
+#   delivers the evidence they assumed. _CHECK_TIMEOUT_MS caps the check run; _DELTA_MAX_FILES / _DELTA_HEAD_LINES bound
+#   the delta.
+# [LEDGER 2026-09-10 @4.101.0] ON (defaults true) — cell-d-k3: resolver held 9/10 PASSING finishes, exit planner mis-called
+#   3/3 real done/not-done decisions, both judging prose + a stale inventory. Efficacy = the next finishing-population cell
+#   (metrics: false-hold rate on passing rows, hold-driven flips, exit-planner mis-calls). =false restores the old inputs.
+#CORTEX_JUDGE_DELTA=true
+#CORTEX_JUDGE_RUN_CHECK=true
+#CORTEX_JUDGE_CHECK_TIMEOUT_MS=45000
+#CORTEX_JUDGE_DELTA_MAX_FILES=8
+#CORTEX_JUDGE_DELTA_HEAD_LINES=60
 #
 # CORTEX_EMPTY_TURN_CONTINUE — the HB-ENDTURN-TERMINAL fix (operator design 2026-09-08). The EndTurn
 # gate's terminal "you stopped — write your answer, do NOT call any tools" reminder can fire on a
@@ -552,6 +575,13 @@ CORTEX_ENDTURN_RESOLVER_ABSTAIN=true
 #   +cost (59 turns). Its "don't-truncate-late-win" value needs the 0.80-1.0 FINISHING population
 #   specifically, not this reject-loop-heavy subset. ⇒ keep dark; re-target the k=5/next cell to the
 #   high-budget_frac finishers (schemelike/make-mips/install-windows/filter-js/pytorch). Stays false.
+# [LEDGER 2026-09-10 @4.99.0] DARK/RETIRED-FOR-k5 (cell-d-k3: k=3, 2×2 flash+pro × ctl/lever, 42/42 rows on the
+#   FINISHING population make-mips/pytorch/schemelike/filter-js (+gcode pro), STDB spine): FIRES (8/18 deadlined lever
+#   rows; pro 5/8) but 0 attributable flips — every fired row failed except schemelike (passes on ctl). Flash +0.17 =
+#   pytorch variance on rows that never fired; pro −0.11 = ctl finished make-mips LATE at 0.91 and the lever cut its twin
+#   off at 0.90/0.94. Fired pro rows still end at ~1.0 budget (the mentor exit eats ~10%; 1 AgentTimeoutError). Only win:
+#   pro tokens −24%. ⇒ stays false; not in the TB2.1 k=5 COMMON. Re-open only with a cheaper exit + ≥0.95 / progress-aware
+#   trigger. Ledger omniclaude-v4/.cortex/bench/r-cell-d-k3-2026-09-10.md.
 #CORTEX_DEADLINE_EXIT_MENTOR=false
 #CORTEX_DEADLINE_EXIT_MENTOR_EFFORT=max
 #CORTEX_DEADLINE_EXIT_MENTOR_BUDGET_TOKENS=2000
@@ -623,6 +653,13 @@ CORTEX_ENDTURN_GATE=true
 # [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.
 # [LEDGER 2026-09-06 @4.93.0] ON=true (reson standard baseline — NOT strict). resolver-k5 ran REQUIREMENTS=true (verified in effective_config), not strict — that is the proven reson baseline; the earlier "strict recommended" is superseded by the actual reson config. Requires GATE=on.
 CORTEX_ENDTURN_REQUIREMENTS=true
+#   CORTEX_ENDTURN_CITATION_LINEWISE — Stage-2 citation grounding matches multi-line quotes LINE-WISE (every non-trivial
+#   line verbatim in the corpus; contiguity not required) and the corpus includes Bash-authored text + the task statement.
+# [LEDGER 2026-09-10 @4.100.0] ON (default true) — cell-d-k3 audit of 84 rejected citations: 47% real lines stitched from
+#   several outputs (rejected as a block), 44% genuine fabrication (still rejected line-wise), 5% Bash-heredoc/task-statement
+#   text (corpus gap), 2% normalization. Replay rescues ~60/84; 0 invented lines pass. =false restores whole-block matching.
+#   Standing metric: endturn_rejections/session (k3 baseline 42/107 calls, 21/26 sessions).
+#CORTEX_ENDTURN_CITATION_LINEWISE=true
 
 # ============================================
 # DECISION STORE (prior-recall + recording)
@@ -933,7 +970,10 @@ CORTEX_SLICE_NUDGE=true
 # 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=
+# [LEDGER 2026-09-10 @4.101.0] ON (default true) — cell-d-k3: the soft nudge fired 23× on 17/42 rows and was IGNORED (61 more
+#   bash slices vs 5 Reads after it; 3 files switched, 15 kept slicing). The block is the escalation the nudge was designed
+#   to hand off to; append-log exemption + MAX=2/file bound the false-positive risk. =false → nudge only.
+#CORTEX_SLICE_BLOCK=true
 #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
@@ -947,6 +987,15 @@ CORTEX_ORIENT_BOOTSTRAP=1
 #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).
 #NEARDUP_NUDGE_AT=12
+#   NEARDUP_SIM_AT / NEARDUP_SIM — HB-LOOP-NEARDUP (2026-09-10): a SIMILARITY near-dup lens for EXECUTING tools
+#   (Bash/Write/Edit; slice-reads excluded): bigram-Dice ≥ NEARDUP_SIM over the last NEARDUP_WINDOW executing calls;
+#   diversify at NEARDUP_SIM_AT, break at 2×. This is what arms CORTEX_LOOP_TOOL_BLOCK on real loops.
+# [LEDGER 2026-09-10 @4.101.0] ON with the breaker — replay of 47 real sessions (cell-l loops + cell-d-k3): the hash
+#   lens peaked at 7-in-30 on every genuine loop (12 unreachable; top hits were paging Reads) → cell-l fired 0×. Similarity
+#   ≥0.9 on executing tools: every real loop crossed 7 (dna-assembly 7/7, gcode python -c 18); no PASSING session did
+#   (max 6). Also fixes the masking bug (a failure-ladder remind hid a near-dup diversify).
+#NEARDUP_SIM_AT=7
+#NEARDUP_SIM=0.9
 
 # CORTEX_LOOP_TOOL_BLOCK — hard loop intervention (operator design 2026-09-07). On a ladder-detected
 # non-converging loop (diversify/break), disables the LOOPING TOOL'S EXECUTOR for one turn (cache-safe:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.101.0",
+  "version": "4.102.0",
   "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": "4.101.0",
+    "@nexus-cortex/core": "4.102.0",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",