@nexus-cortex/cli 4.108.5 → 4.108.8

package/.env.defaults

@@ -756,6 +756,10 @@ CORTEX_ENDTURN_GATE=true
 # ROLLED forward with the dropped messages (memorySource `rolled`); the rung RE-ARMS after each compaction so the last band before the
 # threshold refires every cycle (one whole-conversation helper call per cycle). Live: 28 compactions / 28 fresh covering checkpoints /
 # 0 stale replays (proof run 6). The v2 rule (token distance) replayed ONE stale memory into 27 compactions — never ship a reuse test on tokens.
+# [LEDGER 2026-09-13 @4.108.8] R132 HB-COMPACTION-ESTIMATE: the estimator is now ANCHORED on the provider's last reported prompt_tokens
+# (+ chars/4 of what was appended since; proportional shrink after a drop) — the chars/4-of-the-JSON-envelope heuristic (R129-scaled) is only
+# the fallback before the first usage arrives. Field read on the TB4.0 definitive run (4.108.5): heat-pump-warranty compacted at "760K-1.0M"
+# vs an API max of 151,763 prompt tokens (5-7x over). Compaction rows now bank estimateSource usage-anchored|heuristic + anchorTokens.
 #CORTEX_COMPACTION_CHECKPOINT_PCT=
 #CORTEX_COMPACTION_CHECKPOINT_STEP=
 # CORTEX_COMPACTION_THRESHOLD_TOKENS — TEST/OPS OVERRIDE of the compaction threshold (4.108.3). Unset (default) = the threshold is derived
@@ -768,6 +772,15 @@ CORTEX_ENDTURN_GATE=true
 # proof (/tmp/claude-1000/cmp-test/run.sh, deepseek-flash, threshold 14000, rung 0.6): checkpoint fired, 6 proactive compactions in 17
 # iterations (5 reused the checkpoint at $0), task pinned verbatim in every reminder, final answer 4/4 planted facts — mechanism proven.
 #CORTEX_COMPACTION_THRESHOLD_TOKENS=
+# CORTEX_STATE_DIR — explicit runtime-state root (4.108.6, HB-READONLY-WORKDIR / R131). Unset (default) = <project>/.cortex, but the root
+# is PROBED for writability once per project: a read-only or foreign-owned working directory (a task image that runs the agent as `nobody`
+# in a root-owned /app) falls back to ~/.cortex/projects/<hash>, then <tmpdir>/nexus-cortex/<hash>, with ONE warning. Every runtime writer
+# (tmux metadata/locks, artifact registry, sessions, decisions.jsonl, training samples, resume memory) routes through it, so state
+# persistence is never a boot precondition. Set it to pin the root explicitly (containers, benches, shared checkouts).
+# [LEDGER 2026-09-12 @4.108.6] BUILT + unit-tested (utils/__tests__/stateDir.test.ts); field cause = TB4.0 risk-scorer-replay: cortex-server
+# died at boot (EACCES mkdir /app/.cortex/tmux-sessions/metadata) → empty session. Verify = boot the server as an unprivileged user in a
+# root-owned cwd (docker probe) → boots with the fallback warning.
+#CORTEX_STATE_DIR=
 
 # CORTEX_DELEGATION_HINT — DARK (4.108.1, HB-DELEGATION-DOCTRINE). true = the boot-minimal prompt gains ONE clause naming the Task tool for
 # large / independent / output-heavy sub-tasks (delegate with a self-contained prompt, continue from the summary). The Task tool is
@@ -776,6 +789,18 @@ CORTEX_ENDTURN_GATE=true
 # [LEDGER 2026-09-12 @4.108.1] BUILT + unit-tested (delegationHint.test.ts); DARK — prompt mass on the narrow door is a measured lever, so it
 # needs an A/B on the long-horizon population (TB4.0) before any default. Field read = task_spawn count per session.
 #CORTEX_DELEGATION_HINT=
+# CORTEX_SUBAGENT_TIMEOUT_MS / CORTEX_SUBAGENT_TIMEOUT_MAX_MS — R133 HB-SUBAGENT-TIMEOUT (4.108.8). The Task sub-agent's wall-clock limit was a
+# hardcoded 300 s regardless of the parent's budget: on the TB4.0 definitive run 3 of 6 delegates were cut at 300.0 s (one after 62 turns and
+# 6 files modified, the parent redid the work). Now: the Task input `timeout_ms` wins (clamped to [60 s, remaining-30 s]); else a parent turn
+# deadline (CORTEX_TURN_DEADLINE_MS, set per task by the bench adapter) gives 90% of the REMAINING budget minus 30 s, capped by
+# CORTEX_SUBAGENT_TIMEOUT_MAX_MS if set; else CORTEX_SUBAGENT_TIMEOUT_MS; else 300000. The child receives the same limit as ITS turn deadline
+# only when a real deadline exists. A TIMEOUT result still carries the partial response + Files Modified (inspect on-disk state, don't redo).
+# The outer per-batch abort now honors the resolved Task/Browse limit (it was a Bash-only 150 s cap that killed delegates first).
+# task_spawn decision rows bank timeoutMs[] + remainingMs. Unset = derived as above.
+# [LEDGER 2026-09-13 @4.108.8] BUILT + unit-tested (subAgentTimeout.test.ts, outerToolTimeout.test.ts); validation cell = the 3 TB4.0 tasks
+# whose delegates timed out (mp-checkpoint-consolidation, retro-console-soc, vllm-deepseek-streaming) — PENDING.
+#CORTEX_SUBAGENT_TIMEOUT_MS=
+#CORTEX_SUBAGENT_TIMEOUT_MAX_MS=
 # Stage 4 (4.70.0, requires the gate ON): task-requirements attestation —
 # enumerate each stated requirement with what satisfies it + how it was
 # verified; mutating turns with no checks are challenged. Default OFF.
@@ -871,6 +896,10 @@ CHROMIUM_BIN=
 # Alternate Chromium path honored by Playwright
 PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH=
 # Override the tmux binary used by visual agent monitoring (auto-detected if unset)
+# [LEDGER 2026-09-13 @4.108.8] R134 HB-TMUX-FALLBACK: when tmux is ABSENT, Bash `persistentSession` and CreateArtifactTool persistent/dev
+# process artifacts no longer refuse — they degrade to a detached background process (BackgroundProcessRegistry; poll with BashOutput) with a
+# `[WARN] tmux not available: ...` first line naming the lost semantics (state/cwd/env persistence, attach/reconnect, dashboard restart).
+# Field read: TB4.0 ctr-optimization (no tmux in the image) lost its long-running monitor after 16 refused CreateArtifactTool calls.
 TMUX_BIN=
 # Google Vertex AI project (only when using Vertex instead of the Gemini API)
 GOOGLE_CLOUD_PROJECT=

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.108.5",
+  "version": "4.108.8",
   "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": "4.108.5",
+    "@nexus-cortex/core": "4.108.8",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",