@nexus-cortex/cli 4.124.43 → 4.124.45

package/.env.defaults

@@ -147,6 +147,18 @@ DEFAULT_MODEL_ID=deepseek-flash
 # [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
+# CORTEX_HELPER_MATCH_PROVIDER — R217 (4.124.44, 2026-10-02). HELPER_MODEL_ID and MENTORSHIP_HELPER_MODEL both default to deepseek-flash, so
+# every action model got DeepSeek as its judge / planner / mentor / wall-summarizer / title writer. on = when a role model is NOT explicitly
+# set, it resolves from the ACTION model's provider via the selectHelperModel map (anthropic→claude-haiku-4-5, openai→gpt-4.1-mini,
+# google→gemini-2.5-flash-lite, xai→grok-4.3, deepseek→deepseek-flash; unmapped providers keep deepseek-flash). Explicit settings always
+# win. "Explicit" is decided by VALUE (.env.defaults loads into process.env, so presence cannot tell): a value equal to the shipped
+# default (deepseek-flash) counts as defaulted — to pin deepseek-flash for a non-DeepSeek action model, leave this off. Routed: every
+# HelperModelMiddleware helper/mentor call (generateGuidance = all mentor surfaces + web summary + wall summary + error guidance; doctrine
+# curation; session title; turn summary/prediction; frame-candidate author). Not routed: compaction / context rejection (already
+# provider-mapped), vision hand-off (VISION_HELPER_MODEL), sub-agent model, orchestrator-side labels. off/unset (default) = byte-identical.
+# [LEDGER 2026-10-02 @4.124.44] DARK — BUILT + unit-tested (helperProviderMatch.test.ts: explicit wins, provider matrix, live model switch,
+# off unchanged). NO bench arm yet. evidence: transport map 10-02 (R217).
+#CORTEX_HELPER_MATCH_PROVIDER=
 
 # Model that backs WebSearch / WebFetch tools. Provider auto-detected from ID prefix.
 # When unset, auto-picks based on available API keys (Gemini > Anthropic > XAI),
@@ -601,6 +613,31 @@ CORTEX_LIFT_PLAN=true
 #CORTEX_LIFT_PLAN_TIMEOUT_MS=90000
 #CORTEX_LIFT_PLAN_INTERACTIVE=false
 #CORTEX_LIFT_PLAN_RECON_TIMEOUT_MS=8000
+# CORTEX_INTERACTIVE_PROFILE — R219 HB-INTERACTIVE-PROFILE (DARK, 2026-10-02). The headless levers behind the TB4.0 gains live only in
+#   the bench cell env, so an interactive TUI (neoncortex / fuzzycortex / `cortex` on a terminal) runs without every DARK one. A named
+#   profile, resolved in ONE place (packages/core/src/config/interactiveProfile.ts, applied by bootstrapEnv), turns a curated set on for
+#   INTERACTIVE sessions only (stdin AND stdout are TTYs — the orchestrator's own test) and only for levers you did not set: it sits
+#   ABOVE this shipped file and BELOW the real env, ./.env, <pkg>/.env and ~/.cortex/.env (.env.local still overrides). Filled keys are
+#   recorded in CORTEX_INTERACTIVE_PROFILE_APPLIED (harness-set) and show source `profile` in GET /health/config. Applied at launch.
+#   off (default; unset = byte-identical) | bench-lite =
+#     CORTEX_LOOP_TOOL_BLOCK=true  CORTEX_EMPTY_TURN_CONTINUE=true  CORTEX_WALL_DROP=on  CORTEX_WALL_SUMMARY=on
+#     CORTEX_REASONING_EXHAUST_BACKOFF=false  CORTEX_STEER_INPUTS=full  CORTEX_ORIENT_V2=1
+#   (failure-path-only or steering-input levers: no deadline assumption, no task-tree writes, no new pause before the first action).
+#   Already ON for every session via this file (not the profile's job): ENDTURN_GATE/REQUIREMENTS/RESOLVER(+ABSTAIN), ORIENT_BOOTSTRAP,
+#   SLICE_NUDGE, MENTORSHIP_ENABLED; ENDTURN_TIER=essential and LIFT_PLAN_DOCTRINE=v1 are code defaults.
+#   NOT in bench-lite — NEEDS-ADAPTATION (follow-ups): the lift plan in interactive sessions (CORTEX_LIFT_PLAN_INTERACTIVE stays the only
+#   opener: silent 30-110 s mentor call after the first tool result with no planning-status event to the TUIs, one-shot per orchestrator
+#   so only the first request of a chat is planned, grader-oriented persona); LIFT_PLAN_SCOPE (repair-task edit scope); INVENTORY (whole-tree
+#   walk through execSync blocks the TUI event loop); TURN_STATUS (deadline clock; auto is a no-op without a deadline); VERIFY_SCALE and
+#   RULE_INPUTS/INTERP/HOLDOUT/INDEP (more EndTurn-judge vetoes against a human who wants to stop); ACTION_EFFORT (the TUIs have their own
+#   effort selector). BENCH-ONLY: WORKSPACE_CLEAN (moves project memory out of the project), ORIENT_BASELINE (repair-task revert baseline),
+#   PID1_GUARD (container PID 1 assumption), PLATEAU_STOP (optimisation-task measurement).
+# [LEDGER 2026-10-02 @4.124.44] DARK — BUILT + unit-tested (interactiveProfile.test.ts 16/16: name resolution, interactive vs headless,
+#   explicit env wins, off byte-identical, bootstrapEnv layering, effective-config `profile` source, lift-plan gate; interactiveLiftPlanGate
+#   .integration.test.ts 6/6 both loops: headless plans, interactive + bench-lite does not, explicit CORTEX_LIFT_PLAN_INTERACTIVE=true
+#   plans). NO interactive field read yet. evidence: R219.
+#CORTEX_INTERACTIVE_PROFILE=
+#CORTEX_INTERACTIVE_PROFILE_APPLIED=
 #   CORTEX_ENDTURN_RESOLVER — the finish-side twin of the lift planner: AFTER the mechanical EndTurn gate
 #   accepts, a bounded max-reasoning mentor adjudicates "does the work product meet the task's real
 #   requirements?" MEETS finishes; GAP vetoes with a fix plan (the narrow-door model executes it instead of
@@ -1176,6 +1213,16 @@ CORTEX_ENDTURN_GATE=true
 # reasoning counts inside max_tokens and starves the answer) — both harnesses hit the same wall; this lever changes the RECOVERY and the FRAME.
 # [LEDGER 2026-09-17 @4.115.0] BUILT + unit-tested (turnContract.test.ts). Field: PENDING (tb4 pilot-12, channel arm at effort max).
 #CORTEX_TURN_CONTRACT=
+# CORTEX_FAMILY_PRESETS — R217 (4.124.44, 2026-10-02). promptPreset 'boot-minimal' is set ONLY on the 5 DeepSeek cards, and it is the only
+# prompt that points the model at the `.cortex/orient` script — Claude/GPT/Grok/Gemini got the full corpus and never the orient pointer, so
+# the ORIENT_* / baseline levers were unreachable for them. on = a card WITHOUT its own promptPreset gets its family preset; today ONE
+# generic preset for every family, 'boot-minimal-generic' = the boot-minimal text minus the DeepSeek-tuned "Prefer acting over
+# deliberating." clause (tuned at DeepSeek effort low; fought at high effort, R153), same minimal mass, same orient pointer, same
+# delegation-hint / turn-contract levers. DeepSeek cards unchanged; env CORTEX_PROMPT_MASS / CORTEX_SYSTEM_PROMPT_FILE still win.
+# off/unset (default) = byte-identical (non-DeepSeek cards keep the full corpus).
+# [LEDGER 2026-10-02 @4.124.44] DARK — BUILT + unit-tested (familyPresets.test.ts: per-family selection on/off, DeepSeek identical on/off,
+# off byte-identical). NO bench arm yet. evidence: transport map 10-02 (R217).
+#CORTEX_FAMILY_PRESETS=
 # CORTEX_FINISH_CONFIRM / CORTEX_FINISH_CONFIRM_MIN_REMAINING / CORTEX_FINISH_CONFIRM_MAX — R167 HB-FINISH-CONFIRM (4.116.0, 2026-09-17,
 # pilot-12 hand-curation). The early-finish class is the whole game on the confident-wrong tail: 8/12 first finish attempts per arm
 # had >= 70% of the wall budget left (Terminus 2 too: 8/12 confident-wrong finishes in 15–105 min, its bare "are you sure" changed
@@ -1753,6 +1800,143 @@ MENTORSHIP_ACTIVE_DISCOVERY=false
 # Set to false to opt out (restores the pre-R63 promptless behavior).
 #CORTEX_DELIVER_SYSTEM_PROMPT=false
 
+# CORTEX_RESPONSES_INLINE_REMINDERS — R215 HB-RESPONSES-REMINDERS (DARK, 2026-10-02). The Responses path cut every
+# `<system-reminder>` block out of the conversation and merged it into `instructions`; xAI Responses never receives
+# `instructions` → those reminders were DROPPED there, and on OpenAI they lost their place after the tool output. Levers
+# delivered this way: lift plan, requirement ledger, PID1 note, plateau instruction, lift nudge, deferred-corpus header.
+# on: reminders stay IN PLACE as user input_text items (tags unchanged); a user item the adapter emitted before its
+# function_call_output items is moved after them (tool output first, then the text). `instructions` then carries only
+# the R63 static system prompt (xAI: system-role item at chain start, unchanged). OpenAI + xAI Responses. off: unchanged.
+# [LEDGER 2026-10-02 @4.124.44] DARK — BUILT + unit-tested (transportFixes.test.ts: OpenAI/xAI/streaming request shapes,
+# off = byte-identical). Live probe: DeepSeek /responses accepted function_call → function_call_output → user reminder
+# item (200, model obeyed the reminder). NO bench arm. evidence: transport map 10-02 (R215/R216/R218).
+#CORTEX_RESPONSES_INLINE_REMINDERS=
+# CORTEX_RESPONSES_STOP_REASON — R216 HB-RESPONSES-STOPREASON (DARK, 2026-10-02). extractStopReason returned undefined for
+# the responses and hf-space patterns, so a max-output-tokens cutoff was never classified `truncated` and the wall levers
+# (CORTEX_WALL_DROP / CORTEX_WALL_SUMMARY / CORTEX_REASONING_EXHAUST_BACKOFF) and the truncated-continue nudge never fired
+# there. on: Responses status 'incomplete' + incomplete_details.reason 'max_output_tokens' → 'max_output_tokens' (other
+# incomplete reasons passed through; else the status, e.g. 'completed'); the streaming finalMessage carries the terminal
+# event's status + incomplete_details; hf-space → its finish_reason (synthesized 'stop' / 'tool_calls' — the Space exposes
+# no truncation signal, so hf-space truncation stays invisible). off: unchanged.
+# [LEDGER 2026-10-02 @4.124.44] DARK — BUILT + unit-tested (transportFixes.test.ts: live shapes → classifier truncated +
+# reasoning exhaustion; streaming response.incomplete). Live probe: DeepSeek /responses max_output_tokens 8 → status
+# incomplete, incomplete_details {reason: max_output_tokens}, same in the streaming response.incomplete event.
+# evidence: transport map 10-02 (R215/R216/R218).
+#CORTEX_RESPONSES_STOP_REASON=
+# CORTEX_ANTHROPIC_HISTORY_CACHE — R218 HB-ANTHROPIC-CACHE (DARK, 2026-10-02). Anthropic Messages requests set cache_control
+# only on the system prompt and the last tool, so the conversation history was never cached on Claude. on (and
+# ANTHROPIC_PROMPT_CACHING not false): rolling message breakpoints on the last markable block (not thinking, not empty
+# text) of the previous user message (stable prefix) and the newest user message, within Anthropic's 4-breakpoint cap
+# (system + tool + existing markers counted; one free slot → the stable prefix only). Anthropic provider only — the xAI
+# Messages branch is untouched. off: unchanged.
+# [LEDGER 2026-10-02 @4.124.44] DARK — BUILT + unit-tested (transportFixes.test.ts: placement, cap <= 4, no mutation,
+# send + stream, xAI untouched). Live probe: DeepSeek /anthropic accepted message-level cache_control (200, cache
+# fields 0 — it ignores it). No live Claude probe. evidence: transport map 10-02 (R215/R216/R218).
+#CORTEX_ANTHROPIC_HISTORY_CACHE=
+# APPEND-ONLY REQUEST HISTORY (prompt-cache restructure, 2026-10-02; .cortex/research/caching-audit-2026-10-02.md +
+# caching-rationale-2026-10-02.md). All DARK; unset = byte-identical (harness: every flag-off cell == the committed 220-cell matrix).
+# Measured with the prefix-stability harness (prefixStability.integration.test.ts, PREFIX_EXTRA_ENV / PREFIX_OUT_TAG A/B; reports
+# .cortex/research/prefix-stability-2026-10-02.<tag>.partial.md). The anchor lift (one intended tools bust at the first tool_result) is
+# untouched by all of them.
+# CORTEX_WALL_CACHE_FIX — R221. The HB-WALL-DROP nudge (+ wall summary) is appended to the newest tool_result AFTER that message's
+# canonical conversion was cached (noteRequestUsage runs while the walled turn is the tail), so the retry carried the nudge and every
+# later request silently reverted to the stale copy: a second prefix break + the nudge/summary vanished. on: every in-place mutation of a
+# history message (wall-drop carrier, lift nudge/plan/corpus/ledger, PID1/plateau notes, budget/ladder signals, TURN_STATUS, compute
+# nudge, R26 empty-turn repair, R154 image stub) drops that message's cached conversion. The wall drop itself is unchanged.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + harness-proven: send c1/c2/c3 on anthropic, xai-messages(server-tools off), chat-deepseek
+# went `1→2 tail; 2→3 F1` → `1→2 tail` only (the single intended break at the retry remains); nudge-on-wire N..... → NNNNNN, wall
+# summary persists. Flag off unchanged. Unit: appendOnlyHistory.test.ts, wallGuard.test.ts 11/11, wallGuard.integration 6/6 (+4 skip).
+#CORTEX_WALL_CACHE_FIX=
+# CORTEX_PERSIST_INJECTED — R223. The first request of a user turn sends injected content (repo-state note, deferred-tool announcement,
+# MCP / slash-command notes); history stored the raw text, so every continuation re-rendered that message WITHOUT the notes (one prefix
+# split per user turn + the notes vanished). on: the exact injected bytes are remembered per message uuid and re-sent on every request;
+# session storage, display, title and every text reader keep the raw content (no system-reminder/harness-note text persisted).
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + harness-proven: scenario f (2 user turns) on anthropic, xai-messages(server-tools off),
+# chat-openai, chat-deepseek, gemini x2, hf-space, send + stream: `0→1 lift+F3; 6→7 F3` → `0→1 lift` (harness-note now on every request
+# 0-8). Responses rows unchanged (chaining hides it). Flag off unchanged.
+#CORTEX_PERSIST_INJECTED=
+# CORTEX_APPEND_ONLY_TOOLS — R222. With deferred loading (R43, kept) the filter re-ran on every continuation in allTools order: a newly
+# discovered/used tool was inserted mid-array and the 15-slot recent list evicted. on: the tools array only grows — new tools appended in
+# first-enable order, never evicted or reordered within the orchestrator's lifetime.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + harness-measured: scenario b SearchTools discovery `+8 tools (inserted mid-array at 11)`
+# → `(appended)`, no reorder; eviction not exercised by the harness (unit-tested). NOT a cache win by itself: tools precede system +
+# messages on every wire, so any growth (17→25) is still a full prefix bust once per discovery (harness still reports `2→3 F2`); the
+# flag only removes the reorder/eviction churn. A real fix = a static tools array (cost: R43's token win). Flag off unchanged.
+#CORTEX_APPEND_ONLY_TOOLS=
+# CORTEX_KEEP_MENTOR_MESSAGES — R227. Mentor/guidance messages (injectGuidance / reactive mentorship) were removed from MID-history at
+# turn end (cleanupEphemeralMessages), rewriting the next turn's prefix and shifting the Responses slice checkpoint. on: kept (never
+# persisted to the session file; display strips their system-reminder). Cost: stale guidance stays in context — to be judged in the TUI work.
+# [LEDGER 2026-10-02 @4.124.45] DARK (default OFF by operator decision) — BUILT + harness-proven: scenario e on all non-Responses rows,
+# send + stream: `6→7 F9` gone (mentor insight on the wire in requests 2-9 instead of 2-6). Flag off unchanged.
+#CORTEX_KEEP_MENTOR_MESSAGES=
+# CORTEX_RESPONSES_SLICE_ALL — R228 (bug fix). The EndTurn gate, wall/empty retries, inaction retries and tools-off synthesis set
+# previous_response_id but sent the FULL history (contradicting the e85b68834f slicing design), and never moved the slice checkpoint.
+# on: every chained request sends only the items added since the held response; each of those responses moves the checkpoint (they are
+# main-chain turns: their reply is pushed into history, so updating lastResponseId is correct — not a branch); a wall on a chained session
+# is not dropped locally (the server holds it). Fallback: if the provider reports the held response unavailable (not found / expired /
+# invalid; store off) the chain is dropped and the request is resent ONCE with the full history and NO previous_response_id
+# (responses_chain_fallback event) — send-loop initial request, continuations, gate, retries, synthesis. Streaming initial/continuation
+# (streamRequest) have no fallback yet.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + harness-proven: scenarios a/c1/c3/h on responses-openai, responses-xai, xai default:
+# send a `4→5 NEW-R; 5→6 NEW-R` → one flag left, c1 `1→2, 2→3, 5→6, 6→7 NEW-R` → one flag left; the remaining flag is a harness
+# false positive (two gate attempts push byte-identical reminder text; dump shows each request sends exactly one new item). Fallback
+# unit-tested via isPreviousResponseUnavailable only — no live provider probe. Flag off unchanged.
+#CORTEX_RESPONSES_SLICE_ALL=
+# CORTEX_GEMINI_SYSTEM_FIX — R229 HB-GEMINI-SYSTEM (DARK, 2026-10-02; CORRECTNESS). Gemini never received the system
+# prompt: the non-streaming REST generateContent body had no `system_instruction`; the non-tool requests went through the
+# @google/generative-ai SDK (v0.2.1, v1 endpoint — no systemInstruction support); the google-sdk (@google/genai) paths set a
+# TOP-LEVEL `systemInstruction`, which that SDK drops (GenerateContentParameters = {model, contents, config}). on: REST body
+# carries system_instruction {parts:[{text}]}; non-tool requests with a system prompt use the v1beta REST builders (send +
+# stream); google-sdk puts it in config.systemInstruction (send + stream). The streaming REST builder always sent it. off: unchanged.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + unit-tested (transportCacheFixes.test.ts: 5 Gemini wire shapes, off =
+# byte-identical) + prefix harness (send a, gemini-generateContent + google-sdk: system prompt none → present on all 7
+# requests, byte-stable, pair verdicts unchanged). No live Gemini probe. Default-on candidate (correctness).
+#CORTEX_GEMINI_SYSTEM_FIX=
+# CORTEX_STABLE_TOOL_ORDER — R230 HB-STABLE-TOOL-ORDER (DARK, 2026-10-02). xAI cards with ENABLE_SERVER_SIDE_TOOLS=true run
+# hybrid server+client tools on /v1/responses; the first request of every user turn put the server tools FIRST while the
+# continuations used the original order → the tools array (prefix head) was reordered twice per user turn. on: the caller's
+# original order on every request (adapters/ServerSideToolDetection.ts hybrid branch). off: unchanged.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + unit-tested + prefix harness (send e/f/h, xai default→responses: the per-turn
+# "19→19 tools REORDERED" divergences 2 per cell → 0; the anchor-lift 0→1 bust stays, intended). No live xAI probe.
+#CORTEX_STABLE_TOOL_ORDER=
+# CORTEX_OPENAI_CACHE_KEY — R225 HB-OPENAI-CACHE-KEY (DARK, 2026-10-02). OpenAI chat/completions + Responses bodies carry
+# `prompt_cache_key` = the session id (what xAI Responses already gets) so same-session requests route to the same prompt
+# cache. OpenAI provider only (other chat/completions providers may reject the field). off: unchanged.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + unit-tested + prefix harness (send a: key on 7/7 chat-openai and
+# responses-openai requests, one value per session; chat-deepseek never; pair verdicts unchanged). No live OpenAI probe.
+#CORTEX_OPENAI_CACHE_KEY=
+# CORTEX_ANTHROPIC_AUTO_CACHE — R225 HB-ANTHROPIC-AUTO-CACHE (DARK, 2026-10-02). Anthropic Messages adds the top-level
+# automatic `cache_control` (breakpoint moves with the conversation) beside the explicit system + last-tool markers — only
+# while a breakpoint slot is free (cap 4; R218 CORTEX_ANTHROPIC_HISTORY_CACHE markers counted, so with R218 on it is
+# usually skipped). Needs ANTHROPIC_PROMPT_CACHING. Anthropic provider only — never the xAI Messages branch. off: unchanged.
+# The legacy `prompt-caching-2024-07-31` beta header is still sent (left as is).
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + unit-tested + prefix harness (send a/b anthropic: 2 → 3 markers incl.
+# automatic; with R218 on: 4 max, automatic only on request 0). No live Claude probe.
+#CORTEX_ANTHROPIC_AUTO_CACHE=
+# CORTEX_ANTHROPIC_CACHE_TTL — R225 (DARK, 2026-10-02). 1h: every cache_control the harness emits on the Anthropic path
+# (system, last tool, R218 history, automatic) carries ttl "1h" (uniform, so Anthropic's longer-TTL-first and
+# automatic-vs-last-marker TTL rules hold). Writes cost 2x instead of 1.25x; worth it only when requests sharing the prefix
+# start more than 5 minutes apart (long tool runs). unset | 5m = default 5-minute TTL (no ttl field). Anthropic only.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + unit-tested + prefix harness (all markers ttl 1h, cap <= 4). No live probe.
+#CORTEX_ANTHROPIC_CACHE_TTL=
+# CORTEX_FORCED_CHOICE_FULL_TOOLS — R225 HB-FORCED-CHOICE-FULL-TOOLS (DARK, 2026-10-02). A forced named tool_choice (mentor
+# AskForAdvice, CORTEX_MENTOR_FORCE) narrowed the tools array to the forced tool, rewriting the tools prefix on the forced
+# request and again after it. on: the full tools array is kept; the provider's tool_choice does the forcing. CAUTION:
+# DeepSeek was observed (2026-08-29) to ignore a named choice when the full catalog is present (the reason narrowing exists),
+# and hf-space has no tool_choice on the Gradio wire, so there the force is lost entirely. off: unchanged.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + unit-tested + prefix harness (send d, all transports: the forced pair's first
+# divergence moves from tools (kept 0%) to tool_choice (Anthropic/xAI-messages kept 97%, chat-deepseek 92%, chat-openai 47%,
+# Gemini 92-95%; Responses chained 0%); hf-space stable = force lost). No live probe of choice obedience.
+#CORTEX_FORCED_CHOICE_FULL_TOOLS=
+# CORTEX_STREAM_USAGE — R224a HB-STREAM-USAGE (DARK, 2026-10-02). Streaming chat/completions never asked for usage, so the
+# reassembled final message reported zero tokens (TUI/SSE accounting and cache hit rates invisible). on: streaming requests
+# send stream_options {include_usage: true} and the final message carries the provider's usage object (DeepSeek
+# prompt_cache_hit_tokens, OpenAI prompt_tokens_details). Non-streaming requests unchanged. off: unchanged.
+# [LEDGER 2026-10-02 @4.124.45] DARK — BUILT + unit-tested (request shape + usage carried). Live probe: DeepSeek streaming
+# accepted stream_options (200; usage on the final chunk WITH finish_reason, not a separate choices:[] chunk). The prefix
+# harness cannot reach the streaming builders.
+#CORTEX_STREAM_USAGE=
+
 # Prompt-mass composition (BASH_PLUS_SPEC P6): full (default) | minimal (only
 # the core system prompt; guides/CLAUDE.md/memory dropped) | defer (minimal on
 # turn 1, full corpus appended once at the first tool-result boundary).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.124.43",
+  "version": "4.124.45",
   "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": "4.124.43",
+    "@nexus-cortex/core": "4.124.45",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",