@nexus-cortex/cli 4.108.22 → 4.110.0

package/.env.defaults

@@ -872,6 +872,62 @@ CORTEX_ENDTURN_GATE=true
 # `cortex` idle with summary token turn:1; `agent wait <pane> --until idle` resolves on our report; target by PANE ID or a `rename`d live
 # name (the --agent label is the kind, not a name). Binary resolution order: CORTEX_HERDR_BIN (override) → HERDR_BIN_PATH (herdr's own pane
 # export) → PATH.
+# CORTEX_REASONING_EXHAUST_BACKOFF / CORTEX_REASONING_EXHAUST_BACKOFF_TURNS — R153 HB-REASONING-EXHAUSTION (4.109.0, 2026-09-16). The
+# tb4-flash-v3 sweep found 58 assistant turns in 23 of 63 sessions (a21h 8/7, a21l 4/4) that ended at EXACTLY 65536 output tokens with
+# 100-180K chars of reasoning, no text, no tool call — 3.8M output tokens burned — every one logged as reasoning_only_active and
+# nudged "take your next action", which re-ran the same derivation into the cap again; after 3 the turn ended (coq-block-bound: over at
+# iteration 10 with 97% of 8 h left). ROOT CAUSE: both tool loops passed the TURN'S FIRST stop reason to the empty-response classifier,
+# so the D-E `truncated` carve-out never saw a continuation's finish_reason=length (plus the streaming reassembly hardcoded stop/tool_calls).
+# FIX: lastStopReason is refreshed per response; streamed finish_reason survives; a truncated reasoning-only turn now (a) gets an
+# exhaustion nudge that says the budget was wasted and to act, and (b) arms BACKOFF: the next TURNS continuations (default 2) run one
+# reasoning-effort level lower (max/high → medium → low; repeat exhaustion steps down again); event kind reasoning_exhaustion
+# {iteration, outputTokens, from, level, turns}. Precedence: backoff > effort pulse > request param > card. 'false' keeps the nudge but not
+# the backoff. Streaming loop: the finish_reason=length break is now a warn (the truncation path handles it).
+# [LEDGER 2026-09-16 @4.109.0] BUILT + unit-tested (emptyResponseClassifier.test.ts R153 block). Field: PENDING (7-task R152/R153 patch cell).
+#CORTEX_REASONING_EXHAUST_BACKOFF=
+#CORTEX_REASONING_EXHAUST_BACKOFF_TURNS=
+# (no lever) R154 HB-IMAGE-REJECTION-HEAL (4.109.0, 2026-09-16): retro-console-soc generated a 128x128 8-bit GRAYSCALE PNG, called
+# ReadImage, and DeepSeek answered the next continuation with `400 .messages[290].image[0]: You have uploaded an unsupported image`;
+# the exception escaped after the tool batch, the already-executed guard left the loop, and the R29a synthesis failed on the same block —
+# session over at iteration 133 (43 min of 8 h). Now `orchestrator/imageRejectionHeal.ts` recognises the rejection (4xx + image wording),
+# stubs every user-side image block with a re-encode instruction, and the non-streaming continuation / empty-retry / R29a calls retry the
+# rebuilt request once (event image_rejection_heal {stripped, label, reason}). Streaming loop not healed (chunk-iteration surface).
+# [LEDGER 2026-09-16 @4.109.0] BUILT + unit-tested (imageRejectionHeal.test.ts).
+# (no lever) R155 HB-STATE-DIR-GIT-EXCLUDE (4.109.0, 2026-09-16): nextjs-performance committed a baseline with `git add -A` (sweeping
+# .cortex/sessions + artifacts into the commit) and a later `git checkout <baseline> -- ...` restored a STALE session file over the live
+# one — the banked trajectory starts mid-session. When the state dir resolves to <project>/.cortex and <project>/.git exists, the runtime-
+# state paths (sessions/, artifacts/, training/, decisions.jsonl, memory/, projects/, .write-probe-*) are appended ONCE to .git/info/exclude
+# (marker line; worktree gitdir files followed; best-effort). CORTEX.md stays trackable. `git clean -x` is not covered by design.
+# [LEDGER 2026-09-16 @4.109.0] BUILT + unit-tested (stateDir.test.ts R155).
+# CORTEX_BASH_OOM_PRIORITY — R156 HB-OOM-CHILD-PRIORITY (4.109.0, 2026-09-16). mp-checkpoint-consolidation (tb4-flash-v3) and
+# extract-moves-from-video r3 (tb21-a21l) both died `Command failed (exit 137)` while a model-launched heavy process ran (three 600-s Bash
+# promotions in a row; a video decode): the OOM killer took the agent command including cortex-server — no response, no metrics row,
+# trajectory frozen. The Bash child shell now writes 1000 to /proc/self/oom_score_adj before the command (foreground and background
+# spawns; every descendant inherits it), so the kernel prefers the model's process over the orchestrator and the model sees "Killed" in the
+# tool result instead of the session vanishing. Linux only; best-effort; default on; 'false' = byte-identical command composition.
+# [LEDGER 2026-09-16 @4.109.0] BUILT + unit-tested (executors oomPriority.test.ts). Field: PENDING.
+#CORTEX_BASH_OOM_PRIORITY=
+# CORTEX_BUDGET_CONTINUE_MAX_NUDGES — R157 R151-v2 (4.109.0, 2026-09-16). Field audit of R151 on tb4-flash-v3: the budget line fired
+# in 63/63 sessions and the nudge 13 times, but detectOpenItemsText missed 36 of 52 failing finishes — 8 of them explicit surrenders
+# ("TASK NOT COMPLETE", "I did not prove", "did not fully solve", "honest status report", "fails the task's real success criterion",
+# "unable to") — and every nudged session finished on the very next turn (one-shot). OPEN_ITEMS_RES is broadened with those shapes
+# (tested against all 63 final messages: +8 catches, 2 pass-side false positives costing one nudge each) and the nudge re-arms up to
+# MAX_NUDGES per turn (default 2; 0 = off; max 10) with a firmer second text; event budget_continue_nudge carries {nudge, maxNudges}.
+# [LEDGER 2026-09-16 @4.109.0] BUILT + unit-tested (TurnEndGuards.test.ts R157, timeBudget.test.ts). Field: PENDING.
+#CORTEX_BUDGET_CONTINUE_MAX_NUDGES=
+# CORTEX_MENTOR_CONSULT_BUDGET_TOKENS — R158 HB-CONSULT-BUDGET (4.110.0, 2026-09-16). tb4-flash-v3 pretrain-shard-corruption: the
+# AskForAdvice mentor answer (mentor thinking off, 400-token content cap) came back finish_reason=length, 1721 chars, cut mid-sentence,
+# and the episode banked truncated:false (the flag was only set on the thinking-on empty-content path). Default hint cap 400 -> 800
+# (clamp 100..4000); `truncated` now follows finish_reason=length on every helper call.
+# [LEDGER 2026-09-16 @4.110.0] BUILT + unit-tested (mentorRole.test.ts). Field: PENDING.
+#CORTEX_MENTOR_CONSULT_BUDGET_TOKENS=
+# (no lever) 4.110.0 closes the 4.109.0 disclosures (2026-09-16): R154 image-rejection heal now also covers the STREAMING loop
+# (continuation re-streamed once after the stub; stream empty-retry and stream R29a synthesis wrapped like the non-streaming calls);
+# the sub-agent console fallback prints a progress beat only on a turn change or every 30 s (was every second: 500+ ticker lines per
+# session log); Bash doctrine gains a dependency-manifest rule (live-database-cutover swapped psycopg2-binary for a source build and the
+# grader's fresh install failed). Bench-side (not levers): the adapter sets CORTEX_STATE_DIR=/tmp/.cortex-state so a model's git
+# commands in /app can never clobber the live session (R155 belt-and-braces); bootstrap-executor.sh gates on vCPU per lane
+# (TB2_MIN_VCPU_PER_LANE=3, TB2_VCPU_AUTOSCALE) and passes TB2_VERIFIER_TIMEOUT_MULT (default 2x) as harbor --verifier-timeout-multiplier.
 #CORTEX_HERDR_REPORTING=
 #CORTEX_HERDR_AGENT_NAME=
 #CORTEX_HERDR_BIN=

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.108.22",
+  "version": "4.110.0",
   "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": "4.108.22",
+    "@nexus-cortex/core": "4.110.0",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",