feat: lane bench, codex 0.162 epoch, grok env hardening (0.0.64)

.claude-plugin/marketplace.json

@@ -6,14 +6,14 @@
     "email": "hi@okis.dev"
   },
   "description": "Multi-model orchestration marketplace for Claude Code.",
-  "version": "0.0.63",
+  "version": "0.0.64",
   "plugins": [
     {
       "name": "grok",
       "source": "./plugins/grok",
       "displayName": "Grok Companion",
       "description": "Local Grok CLI delegation: task, review, resumable history, best-of-n tournaments, background jobs, stats, and setup health checks.",
-      "version": "0.0.63",
+      "version": "0.0.64",
       "author": {
         "name": "Harry Yep"
       },
@@ -34,7 +34,7 @@
       "source": "./plugins/codex",
       "displayName": "Codex Companion",
       "description": "First party local Codex CLI delegation for tasks, reviews, resumable threads, and durable background jobs.",
-      "version": "0.0.63",
+      "version": "0.0.64",
       "author": {
         "name": "Harry Yep"
       },
@@ -55,7 +55,7 @@
       "source": "./plugins/cursor",
       "displayName": "Cursor Companion",
       "description": "Local Cursor Agent CLI delegation: multi family consults, Composer implementation in owned worktrees, review, resumable history, background jobs, and setup health checks.",
-      "version": "0.0.63",
+      "version": "0.0.64",
       "author": {
         "name": "Harry Yep"
       },
@@ -76,7 +76,7 @@
       "source": "./plugins/fusion",
       "displayName": "Fusion Orchestrator",
       "description": "Multi-model orchestration: tier agents, routing rules, blind panel, ultra fleet, model config, and drift doctor.",
-      "version": "0.0.63",
+      "version": "0.0.64",
       "author": {
         "name": "Harry Yep"
       },

CHANGELOG.md

@@ -1,5 +1,14 @@
 # changelog
 
+## 0.0.64
+
+- the codex companion is verified on codex-cli 0.162.1 (#72). the source diff from rust-v0.157.1 changes none of the flags, jsonl events, resume, output schema, review path, login status, models cache, or rollout layout the companion relies on, and setup, `--output-schema`, thread resume, and native review pass live on 0.162.1. the tested interval moves to `[0.154.0, 0.163.0)` and `verified-versions.json` to 0.162.1. `Flex capacity unavailable.` now classifies as `rate_limited`, and the content filter and stock cybersecurity and biological risk refusals classify as `refused` instead of `error`.
+- the grok child env covers the 1.0.52 surfaces (#72): `GROK_TURN_SUMMARY=false` stops the extra grok-4.5 summary call per turn, `GROK_FILE_ACCELERATION=false` is pinned, and inherited `GROK_SANDBOX_MODE`, `GROK_ARTIFACTS_BIND_REMOUNT`, `GROK_FILE_ACCELERATION_ROUTES`, `GROK_CURSOR_WORKER_API_BASE`, and `GROK_CURSOR_WORKER_COMMAND` no longer reach managed runs. all eighteen bridge pins are confirmed effective on the installed 1.0.52. the grok tested interval stays `[1.0.14, 1.0.42)` until a live pass (#75), which an exhausted grok balance and the OrbStack write refusal block on both hosts today.
+- the docs stop claiming the bridge variables cover every compatibility import. grok enables the claude code plugins that `~/.claude/settings.json` enables, and since 1.0.52 their hooks and mcp servers can start inside a managed run unless `~/.grok/config.toml` sets `[claude_compat] imported = true` or lists them in `[plugins] disabled`. security, the readme, the grok contract, the rules, and the doctor now say so, and also fix the stale `[1.0.14, 1.0.31)` interval, the "entire grok home" write root, and the `modelUsage` field names.
+- `bench/lanes/` measures one routing lane at a time (#70). `run.mjs` sends a task brief through one companion with an explicit model and effort, verifies outside the workspace, and appends a jsonl record; `summarize.mjs` groups the records. the first snapshot, `bench/results/lanes-2026-10-13/`, runs composer-2.5, composer-2.5-fast, and gpt-6-luna on T05, T06, and T09, plus four blind consults through muse-spark-1.3, gemini-3.8-flash, kimi-k3, glm-5.2, and deep-reasoner. composer stays co-equal with grok burst (0 of 6 on T06, where luna passes 9 of 9), muse-spark-1.3 stays the diversity default, kimi-k3 rises to intelligence 4, and the five cursor rows trade their provisional notes for the measurements.
+- `fusion:trivial-worker` pins `claude-haiku-5-5` (#73).
+- the consults surfaced a latent double removal in the T01 reference solution, tracked in #74.
+
 ## 0.0.63
 
 - cursor joins as the third peer engine. the new `cursor` plugin drives the cursor agent cli (`cursor-agent`, build 2026.10.01-e373342) headlessly with consult, write, and review modes, resumable chats, background jobs, history, a model catalog, and setup. fusion routes it under two protected roles: `diversity`, a read only consult on a model family no other lane serves (google, meta, moonshot, zhipu, cursor composer), and `burst`, composer implementation inside orchestrator owned worktrees. it never runs auto, never serves the claude family, and only stands in for another family's weights when that family's native lane is down on quota.