@nexus-cortex/cli 4.124.46 → 4.124.48

package/.env.defaults

@@ -557,7 +557,19 @@ CORTEX_ALLOW_CMD_SUBSTITUTION=true
 # R37/R38 benchmarks: hybrid (true) is 20-26% faster than client-only with equal accuracy.
 ENABLE_SERVER_SIDE_TOOLS=true
 # Default API pattern for XAI models at registration time (ENABLE_SERVER_SIDE_TOOLS=true
-# overrides at request time). Options: messages | responses
+# overrides at request time). Options: messages | responses | chat
+#   chat = https://api.x.ai/v1/chat/completions (Bearer XAI_API_KEY) through the SAME chat/completions builder DeepSeek uses
+#   (append-only prefix cache, reasoning_content replay, x-grok-conv-id header). Client tools only: a chat-mode card registers
+#   no server-side tools, so ENABLE_SERVER_SIDE_TOOLS never re-routes it to /v1/responses. reasoning_effort is sent only for
+#   cards that declare an effort (grok-4.3-class; request/CORTEX_ACTION_EFFORT wins, max→high) — never grok-build-0.1 (400).
+#   Applies only to UN-PINNED xAI cards (grok-4.6 / grok-build-0.1 pin messages). Bench arms should select the pinned cards
+#   instead: `grok-4.3-chat` / `grok-build-0.1-chat`. Streaming usage needs CORTEX_STREAM_USAGE=on (same as DeepSeek); the
+#   system prompt rides CORTEX_DELIVER_SYSTEM_PROMPT (same R63 gate as every chat/completions provider).
+# [LEDGER 2026-10-03 @4.124.47] DARK — BUILT: XAI_API_MODE value `chat` + cards grok-4.3-chat / grok-build-0.1-chat (third xAI
+#   transport, additive; /v1/messages path untouched — prefix harness xai-messages rows byte-identical off/on). Unit-tested
+#   (xaiChatTransport.test.ts) + prefix rows xai-chat(grok-4.3-chat|grok-build-0.1-chat) append-only. Live 2026-10-03: grok-4.3 (effort high)
+#   + grok-build-0.1 (no effort) both finish tool_calls. NOTE: xAI completion_tokens EXCLUDES reasoning_tokens (DeepSeek's include
+#   them) — canonical outputTokens under-counts billed output here; use reasoningTokens / costUsd (cost_in_usd_ticks). Never benched.
 XAI_API_MODE=messages
 # OpenAI request surface. Options: chat/completions | responses (opt into hosted tools)
 OPENAI_API_MODE=
@@ -1977,6 +1989,42 @@ MENTORSHIP_ACTIVE_DISCOVERY=false
 # explicit request param still wins). off = unchanged (byte-identical).
 # [LEDGER 2026-10-03 @4.124.46] DARK — BUILT (unit tests; turn it on in every non-DeepSeek cross-provider arm).
 #CORTEX_ACTION_EFFORT_FIRST=
+#
+# CORTEX_GEMINI_EXPLICIT_CACHE — HB-GEMINI-EXPLICIT-CACHE (DARK, 2026-10-03; stack-portability §"GEMINI EXPLICIT cachedContents
+# FEASIBILITY"). Gemini implicit caching is partial on gemini-3-flash-preview (fixed ~12K head only) and NONE on gemini-3.8-flash;
+# explicit cachedContents cached 13,405/13,414 on both (live 2026-10-03). on: the Gemini builders (REST send + stream, @google/genai
+# send + stream) snapshot (model, system, tools) + history up to (not including) the newest turn as a cachedContents once it reaches
+# the model minimum (3.x 4,096 / 2.5 2,048 tokens, ai.google.dev/gemini-api/docs/caching), then send cachedContent + only the turns
+# after the snapshot with NO system/tools/toolConfig (Gemini 400s that pair). Re-snapshot when the uncached tail passes
+# CORTEX_GEMINI_CACHE_RESNAPSHOT_TOKENS, when the history before the snapshot is rewritten (hash check), or near expiry; a
+# system/tools change (anchor lift) = new snapshot. Superseded snapshots are DELETEd; orchestrator cleanup DELETEs the rest. A forced
+# tool_choice request bypasses the cache. Any 400/403/404 on a cached request = the full request once + slot dropped; a failed
+# create = full request + backoff. Logs `[gemini-cache]` lines (CORTEX_GEMINI_CACHE_QUIET=true silences). Cost (pricing page,
+# 2026-10-03): creation = the prefix at the normal input rate once; cached reads 3 Flash $0.05/M (input $0.50), 3.8 Flash $0.075/M
+# (input $0.75, through 2026-12-31); storage 3 Flash $1.00, 3.8 Flash $0.50 per M tokens per hour. off: unchanged (byte-identical).
+# [LEDGER 2026-10-03 @4.124.47] DARK — BUILT (16 unit tests on a fake Gemini API; off = byte-identical send + stream) + one live
+# 5-turn tool loop on gemini-3-flash-preview + gemini-3.8-flash through the built dist (see the 4.124.47 changeset). No bench arm yet.
+#CORTEX_GEMINI_EXPLICIT_CACHE=
+#
+# CORTEX_GEMINI_CACHE_TTL_S — HB-GEMINI-EXPLICIT-CACHE: snapshot TTL in seconds (min 60). A snapshot used in the second half of its
+# life is PATCHed back to the full TTL. Storage is billed per token-hour, so the TTL bounds the cost of an orphaned snapshot.
+# [LEDGER 2026-10-03 @4.124.47] DARK — BUILT (inert unless CORTEX_GEMINI_EXPLICIT_CACHE=on). Default 300.
+#CORTEX_GEMINI_CACHE_TTL_S=300
+#
+# CORTEX_GEMINI_CACHE_RESNAPSHOT_TOKENS — HB-GEMINI-EXPLICIT-CACHE: re-snapshot a longer prefix once the uncached tail (history after
+# the snapshot, newest turn excluded; chars/4 estimate) exceeds this many tokens (min 1024). Lower = more creations (each billed at
+# the full input rate), higher = more uncached input per request.
+# [LEDGER 2026-10-03 @4.124.47] DARK — BUILT (inert unless CORTEX_GEMINI_EXPLICIT_CACHE=on). Default 16000.
+#CORTEX_GEMINI_CACHE_RESNAPSHOT_TOKENS=16000
+#
+# CORTEX_GEMINI_CACHE_MIN_TOKENS — HB-GEMINI-EXPLICIT-CACHE: override the per-model minimum cacheable size (default 4096 for 3.x
+# incl. gemini-3-flash-preview, which the docs table does not list; 2048 for 2.5).
+# [LEDGER 2026-10-03 @4.124.47] DARK — BUILT (inert unless CORTEX_GEMINI_EXPLICIT_CACHE=on). Default: per model.
+#CORTEX_GEMINI_CACHE_MIN_TOKENS=
+#
+# CORTEX_GEMINI_CACHE_QUIET — HB-GEMINI-EXPLICIT-CACHE: true silences the `[gemini-cache]` stderr lines.
+# [LEDGER 2026-10-03 @4.124.47] DARK — BUILT (inert unless CORTEX_GEMINI_EXPLICIT_CACHE=on). Default false.
+#CORTEX_GEMINI_CACHE_QUIET=
 
 # Prompt-mass composition (BASH_PLUS_SPEC P6): full (default) | minimal (only
 # the core system prompt; guides/CLAUDE.md/memory dropped) | defer (minimal on

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nexus-cortex/cli",
-  "version": "4.124.46",
+  "version": "4.124.48",
   "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": "4.124.46",
+    "@nexus-cortex/core": "4.124.48",
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.0",
     "commander": "^11.0.0",