| # Ruflo v3.32.2 ? stable Codex, hooks, security, and plugin integration update | |
| Ruflo v3.32.2 is a stable release. It contains no alpha tag and is published as `latest` for `ruflo`, `claude-flow`, and `@claude-flow/cli`. | |
| ## Why a release was required | |
| The reported Codex failures came from immutable cached plugin versions and an MCP cold-start budget that was too short: | |
| - `ruflo-core/0.2.2/hooks/hooks.json` and `ruflo-cost-tracker/0.26.0/hooks/hooks.json` could be cached as empty/invalid content, producing `expected value at line 1 column 1`. | |
| - Once hook loading failed, the `ruflo` MCP server could still be launched, but a 30-second Codex startup limit was too short for a cold `npx` resolution and plugin initialization. |
Ruflo v3.32.1 fixes the Codex integration failures that appeared as hook JSON parse errors, incomplete MCP startup, and 30-second startup timeouts?especially on Windows.
Status: research only; no service, harness, cloud resource, or deployment has been created.
Research date: 2026-07-16
Locally verified: metaharness@0.3.1, @metaharness/harness@0.1.0, @metaharness/host-claude-code@0.1.2, @metaharness/host-codex@0.1.2, and codex-cli 0.142.5.
A small, continuously available coding-agent service is feasible with MetaHarness as the generated harness/control-plane layer, a durable job queue, and replaceable Claude Code and Codex execution adapters. The simplest credible GCP topology is an authenticated Cloud Run API plus Pub/Sub and a Cloud Run worker pool kept at one or more instances; the worker pulls jobs, creates a disposable repository workspace, invokes either claude -p or Codex, publishes artifacts and status, and destroys the workspace.
Issue: ruvnet/ruflo#2661 (P0)
Fix: ruvnet/ruflo#2662, shipped starting in @claude-flow/cli@3.27.0
Every Git worktree of a ruflo project started its own autonomous daemon, each daemon independently scheduled three Claude-powered background workers, and nothing coordinated across worktrees — so the number of autonomous Claude launches per hour scaled linearly with worktree count, with no ceiling.
TL;DR: RuVector — an open-source Rust vector database with HNSW indexing, WASM bindings, and Postgres integration — just shipped local (no-API-key) embedding generation via Lattice on both the Rust crate (ruvector-core@2.3.0) and the npm/WASM package (ruvector-extensions@0.1.2), fixed 3 real RustSec CVEs, and turned cargo audit + cargo deny fully green after they'd been failing on main. Full release notes: ruvector-core-v2.3.0.
Most vector-search tutorials assume you're calling OpenAI or Cohere for embeddings. That's fine for a demo, but it means every insert and every query round-trips to a third party, costs money per call, and leaks your data off-box. RuVector's new Lattice integration gives you a CPU-native, pure-Rust embed
Published on 2026-07-08 from branch fix/main-v3-ci-red-shim-types, targeting source commit e09843303232b0199d5c8629ec3bd5e233adc5a7.
Release tracker: ruvnet/ruflo#2614 PR: ruvnet/ruflo#2604
claude-flow@3.25.5
ruflo has shipped thousands of releases. The number is
3.25.4right now. If you were handed that string cold — no changelog, no README — what could you tell me about it? "It's newer than 3.25.3." That's it.Meanwhile,
3.25.4shipped 40 new MCP tools, a new agent type, a memory-schema tweak, and re-signed the witness manifest — all invisible in the number. That's not a versioning discipline problem. It's a versioning scheme problem.This gist explains Agent-Native Versioning (ANV) — a small, backward-compatible change to how ruflo versions itself so the string carries actual information instead of ordering alone.
Based on the ruvnet prior-art dossier, the organization lists 23 distinct "scoped global-first" claims categorized at a medium confidence level. Rather than asserting that they invented the underlying primitives (like HNSW, MCP, or post-quantum crypto), these claims are strictly scoped to specific syntheses or first open-source runnable implementations. The primary medium-confidence claims include:
Read the model's mind while it thinks. A dependency-free, runtime interpretability primitive that turns the Jacobian Lens from Anthropic's 2026 global-workspace paper into a production audit + governance tool for open-weight language models.
📦 Live on npm: @metaharness/workspace-lens@0.1.0 · npm i @metaharness/workspace-lens · MIT · source & PR
There is no
@ruvector/lattice-wasmpackage — it 404s on npm, and no "Lattice" embedder package exists in the ruvector ecosystem. The models below (bge / qwen3-0.6b / paraphrase-miniLM) exist only in a Rust ONNX example, not a publishable package. What actually shipped in 3.25.0 is a fail-closed, optional adapter seam that degrades to ruvector-ONNX → hash when the (nonexistent) package is absent — so it is DORMANT / no-op today and causes no regression, but it is NOT a working multi-model embedder. The rest of this document describes the intended design; treat it as a proposal for a real embedder, not a shipped capability. Follow-up: remove the seam or wire it to a real embedder.
TL;DR — ruflo now supports a real, multi-model WASM embedder as the primary embedding tier, ahead of the existing ONNX/hash path. It's optional, fail-closed, and zero-regression: if the package isn't installed, embe