vrr/ruvector
2
0
Fork 0
mirror of https://github.com/ruvnet/RuVector.git synced 2026-05-30 03:53:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
ruvector/CLAUDE.md

9.3 KiB
Raw Permalink Blame History

Claude Code Configuration - Claude Flow V3

Behavioral Rules (Always Enforced)

  • Do what has been asked; nothing more, nothing less
  • NEVER create files unless they're absolutely necessary for achieving your goal
  • ALWAYS prefer editing an existing file to creating a new one
  • NEVER proactively create documentation files (*.md) or README files unless explicitly requested
  • NEVER save working files, text/mds, or tests to the root folder
  • Never continuously check status after spawning a swarm — wait for results
  • ALWAYS read a file before editing it
  • NEVER commit secrets, credentials, or .env files

Publishing (crates.io & npm)

  • Credentials are in .env (project root) and ~/.cargo/credentials.toml — NEVER commit or log these
  • npm is authenticated as ruvnet — verify with npm whoami
  • NEVER echo, cat, or print credential files. Source .env only via source .env
  • Publish order for solver crates: ruvector-solver first (no deps), then ruvector-solver-wasm and ruvector-solver-node (depend on solver)
  • Always run cargo publish --dry-run --allow-dirty before real publish
  • ruvector-profiler has publish = false — intentionally not publishable

npx ruvector (npm)

  • Package: ruvector on npm, published as ruvnet
  • Location: npm/packages/ruvector/
  • Current version: check npm/packages/ruvector/package.json
  • Pre-publish checklist:
    1. cd npm/packages/ruvector
    2. Update version in package.json AND bin/mcp-server.js (2 occurrences of version string)
    3. node -c bin/cli.js && node -c bin/mcp-server.js (syntax check)
    4. npm test (55 CLI + integration tests must pass)
    5. npm publish --access public
  • Key files:
    • bin/cli.js (~8500 lines) — 48 commands, 12 groups (brain, edge, identity, mcp, rvf, hooks, llm, sona, route, gnn, attention, embed)
    • bin/mcp-server.js (~3500 lines) — 91 MCP tools, stdio + SSE transports
    • test/integration.js — module loading, type defs, package structure
    • test/cli-commands.js — 55 CLI command tests
  • chalk ESM fix: chalk v5 is ESM-only, we use CJS. Always use: const _chalk = require('chalk'); const chalk = _chalk.default || _chalk;
  • Lazy loading: GNN, attention, ora are lazy-loaded for ~55ms startup. Do NOT convert to eager imports.
  • Peer deps (optional): @ruvector/pi-brain, @ruvector/ruvllm, @ruvector/router

π.ruv.io (Cloud Run)

  • Service: ruvbrain in us-central1 on project ruv-dev
  • Source: crates/mcp-brain-server/ — axum Rust server
  • Landing page: crates/mcp-brain-server/static/index.html (embedded via include_str!)
  • Origin slideshow: crates/mcp-brain-server/static/origin.html
  • Deploy:
    1. Edit HTML in crates/mcp-brain-server/static/
    2. gcloud builds submit --config=crates/mcp-brain-server/cloudbuild.yaml --project=ruv-dev .
    3. gcloud run deploy ruvbrain --image gcr.io/ruv-dev/ruvbrain:latest --region us-central1 --project ruv-dev
  • Dockerfile: crates/mcp-brain-server/Dockerfile — strips examples/ from workspace before build
  • Domain: π.ruv.io (also pi.ruv.io) → Cloud Run custom domain mapping

Rust Crates (crates.io)

  • Publish order: Check inter-crate path = dependencies. Publish leaf crates first.
  • Version deps: Before publishing, convert path = "../foo" to version = "x.y" in Cargo.toml
  • Dry run: cargo publish --dry-run --allow-dirty -p <crate-name>
  • EXO-AI crates: Published as v0.1.1 (ruvector-exo-core, ruvector-exo-vision, etc.)

File Organization

  • NEVER save to root folder — use the directories below
  • Use /src for source code files
  • Use /tests for test files
  • Use /docs for documentation and markdown files
  • Use /config for configuration files
  • Use /scripts for utility scripts
  • Use /examples for example code

Project Architecture

  • Follow Domain-Driven Design with bounded contexts
  • Keep files under 500 lines
  • Use typed interfaces for all public APIs
  • Prefer TDD London School (mock-first) for new code
  • Use event sourcing for state changes
  • Ensure input validation at system boundaries

Project Config

  • Topology: hierarchical-mesh
  • Max Agents: 15
  • Memory: hybrid
  • HNSW: Enabled
  • Neural: Enabled

Build & Test

# Build
npm run build

# Test
npm test

# Lint
npm run lint
  • ALWAYS run tests after making code changes
  • ALWAYS verify build succeeds before committing

Security Rules

  • NEVER hardcode API keys, secrets, or credentials in source files
  • NEVER commit .env files or any file containing secrets
  • Always validate user input at system boundaries
  • Always sanitize file paths to prevent directory traversal
  • Run npx @claude-flow/cli@latest security scan after security-related changes

Concurrency: 1 MESSAGE = ALL RELATED OPERATIONS

  • All operations MUST be concurrent/parallel in a single message
  • Use Claude Code's Task tool for spawning agents, not just MCP
  • ALWAYS batch ALL todos in ONE TodoWrite call (5-10+ minimum)
  • ALWAYS spawn ALL agents in ONE message with full instructions via Task tool
  • ALWAYS batch ALL file reads/writes/edits in ONE message
  • ALWAYS batch ALL Bash commands in ONE message

Swarm Orchestration

  • MUST initialize the swarm using CLI tools when starting complex tasks
  • MUST spawn concurrent agents using Claude Code's Task tool
  • Never use CLI tools alone for execution — Task tool agents do the actual work
  • MUST call CLI tools AND Task tool in ONE message for complex work

3-Tier Model Routing (ADR-026)

Tier Handler Latency Cost Use Cases
1 Agent Booster (WASM) <1ms $0 Simple transforms (var→const, add types) — Skip LLM
2 Haiku ~500ms $0.0002 Simple tasks, low complexity (<30%)
3 Sonnet/Opus 2-5s $0.003-0.015 Complex reasoning, architecture, security (>30%)
  • Always check for [AGENT_BOOSTER_AVAILABLE] or [TASK_MODEL_RECOMMENDATION] before spawning agents
  • Use Edit tool directly when [AGENT_BOOSTER_AVAILABLE]

Swarm Configuration & Anti-Drift

  • ALWAYS use hierarchical topology for coding swarms
  • Keep maxAgents at 6-8 for tight coordination
  • Use specialized strategy for clear role boundaries
  • Use raft consensus for hive-mind (leader maintains authoritative state)
  • Run frequent checkpoints via post-task hooks
  • Keep shared memory namespace for all agents
npx @claude-flow/cli@latest swarm init --topology hierarchical --max-agents 8 --strategy specialized

Swarm Execution Rules

  • ALWAYS use run_in_background: true for all agent Task calls
  • ALWAYS put ALL agent Task calls in ONE message for parallel execution
  • After spawning, STOP — do NOT add more tool calls or check status
  • Never poll TaskOutput or check swarm status — trust agents to return
  • When agent results arrive, review ALL results before proceeding

V3 CLI Commands

Core Commands

Command Subcommands Description
init 4 Project initialization
agent 8 Agent lifecycle management
swarm 6 Multi-agent swarm coordination
memory 11 AgentDB memory with HNSW search
task 6 Task creation and lifecycle
session 7 Session state management
hooks 17 Self-learning hooks + 12 workers
hive-mind 6 Byzantine fault-tolerant consensus

Quick CLI Examples

npx @claude-flow/cli@latest init --wizard
npx @claude-flow/cli@latest agent spawn -t coder --name my-coder
npx @claude-flow/cli@latest swarm init --v3-mode
npx @claude-flow/cli@latest memory search --query "authentication patterns"
npx @claude-flow/cli@latest doctor --fix

Available Agents (60+ Types)

Core Development

coder, reviewer, tester, planner, researcher

Specialized

security-architect, security-auditor, memory-specialist, performance-engineer

Swarm Coordination

hierarchical-coordinator, mesh-coordinator, adaptive-coordinator

GitHub & Repository

pr-manager, code-review-swarm, issue-tracker, release-manager

SPARC Methodology

sparc-coord, sparc-coder, specification, pseudocode, architecture

Memory Commands Reference

# Store (REQUIRED: --key, --value; OPTIONAL: --namespace, --ttl, --tags)
npx @claude-flow/cli@latest memory store --key "pattern-auth" --value "JWT with refresh" --namespace patterns

# Search (REQUIRED: --query; OPTIONAL: --namespace, --limit, --threshold)
npx @claude-flow/cli@latest memory search --query "authentication patterns"

# List (OPTIONAL: --namespace, --limit)
npx @claude-flow/cli@latest memory list --namespace patterns --limit 10

# Retrieve (REQUIRED: --key; OPTIONAL: --namespace)
npx @claude-flow/cli@latest memory retrieve --key "pattern-auth" --namespace patterns

Quick Setup

claude mcp add claude-flow -- npx -y @claude-flow/cli@latest
npx @claude-flow/cli@latest daemon start
npx @claude-flow/cli@latest doctor --fix

Claude Code vs CLI Tools

  • Claude Code's Task tool handles ALL execution: agents, file ops, code generation, git
  • CLI tools handle coordination via Bash: swarm init, memory, hooks, routing
  • NEVER use CLI tools as a substitute for Task tool agents

Support