ruvector/Cargo.toml
rUv e2350b759f
fix(core): HNSW correctness fixes, k=0 guard, sorted results, cross-integration helpers (v2.2.3) (#502)
* fix(core): correctness + safety fixes in HNSW/flat index + cross-integration helpers (v2.2.3)

Correctness fixes:
- hnsw: `DistanceFn::eval` now clamps distance to 0.0 — prevents hnsw_rs
  internal BinaryHeap assertion panic when floating-point rounding yields a
  marginally-negative cosine/euclidean distance for near-identical vectors
- hnsw: `set_ef_search` was a silent no-op; now correctly writes to
  `config.ef_search` so callers can tune recall at query time
- hnsw: `search_with_ef` clamps `ef_search` to `max(ef_search, k)` to
  prevent silent under-recall when ef_search < k (hnsw_rs constraint)
- hnsw: `search_with_ef` now explicitly returns an empty slice for k=0
  instead of forwarding to hnsw_rs which may panic
- hnsw: `search_with_ef` returns early (empty slice) when index is empty
  to avoid hnsw_rs BinaryHeap `.peek().unwrap()` panic on zero-element index
- hnsw: results are now explicitly sorted by ascending distance; hnsw_rs
  does not guarantee this order in all code paths
- hnsw: deserialization rebuilds the HNSW graph in index order
  (sorted by idx) and uses an O(n) HashMap lookup instead of O(n^2)
  linear search over the vectors vec during restore
- flat: added k=0 guard (returns empty slice, no panic)
- flat: switched sort to `sort_unstable_by` with a `partial_cmp` fallback
  to handle NaN distances gracefully and improve throughput on large sets

API improvement:
- types: `HnswConfig::default()` now uses `max_elements=1_000_000` (was
  10_000_000) and `m=16/ef_construction=100` to avoid excessive upfront
  memory allocation in the common case; large-index callers can still
  set `max_elements` explicitly

New module:
- integration: `FannAdapter` and `SemanticSearchAdapter` — thin wrappers
  that make ruvector-core directly usable from ruv-FANN (layer-embedding
  storage + retrieval) and sparc (semantic file search by embedding query).
  Includes `normalize()` and `cosine_similarity()` free-standing utilities.

Tests (4 new integration, 3 new unit):
- test_hnsw_search_k_zero: k=0 returns empty, no panic
- test_hnsw_results_sorted_ascending: verifies window[i].score <= window[i+1].score
- test_hnsw_set_ef_search_updates_config: set_ef_search writes through to config
- test_hnsw_search_with_ef_clamps_to_k: ef < k still returns results
- flat: test_flat_index_k_zero, test_flat_index_results_sorted
- integration: FannAdapter and SemanticSearchAdapter roundtrip tests

Version bump: 2.2.2 → 2.2.3

Co-Authored-By: claude-flow <ruv@ruv.net>

* style: cargo fmt ruvector-core
2026-05-23 03:37:35 -04:00

331 lines
12 KiB
TOML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

[workspace]
exclude = ["crates/micro-hnsw-wasm", "crates/ruvector-hyperbolic-hnsw", "crates/ruvector-hyperbolic-hnsw-wasm", "examples/ruvLLM/esp32", "examples/ruvLLM/esp32-flash", "examples/edge-net", "examples/data", "examples/ruvLLM", "examples/delta-behavior", "crates/rvf", "crates/rvf/*", "crates/rvf/*/*", "examples/rvf-desktop", "crates/mcp-brain-server",
# ruvector-postgres is a pgrx-based PostgreSQL extension. Its build script
# requires `$PGRX_HOME` set up via `cargo install cargo-pgrx --version 0.12.9`
# and `cargo pgrx init`, which downloads and builds multiple Postgres
# versions. Keep it out of default workspace builds so `cargo build --workspace`
# works in stock environments. Build it explicitly with `cargo build -p ruvector-postgres`
# after running pgrx init.
"crates/ruvector-postgres",
# Iter 219 (closes ADR-178 Gap E folded into Gap B): the hailo
# crates rejoined the workspace once the iter-218 ruvector-core
# path dep + EmbeddingProvider impls landed. The `hailo` feature
# stays opt-in (only `cargo build --features hailo,cpu-fallback`
# pulls libhailort + candle), so workspace builds on stock x86
# still compile without Pi-specific tooling.
# ruos-thermal: Pi 5 thermal supervisor skeleton (ADR-174). Standalone
# for now; joins workspace once daemon mode + Unix socket protocol
# land in iters 92-97.
"crates/ruos-thermal"]
members = [
"crates/ruvector-acorn",
"crates/ruvector-acorn-wasm",
"crates/ruvector-rabitq",
"crates/ruvector-rabitq-wasm",
"crates/ruvector-rulake",
"crates/ruvector-core",
"crates/ruvector-node",
"crates/ruvector-wasm",
"crates/ruvector-cli",
"crates/ruvector-bench",
"crates/ruvector-metrics",
"crates/ruvector-filter",
"crates/ruvector-router-core",
"crates/ruvector-router-cli",
"crates/ruvector-router-ffi",
"crates/ruvector-router-wasm",
"crates/ruvector-server",
"crates/ruvector-snapshot",
"crates/ruvector-tiny-dancer-core",
"crates/ruvector-tiny-dancer-wasm",
"crates/ruvector-tiny-dancer-node",
"crates/ruvector-collections",
"crates/ruvector-cluster",
"crates/ruvector-raft",
"crates/ruvector-replication",
"crates/ruvector-graph",
"crates/ruvector-graph-node",
"crates/ruvector-graph-wasm",
"crates/ruvector-gnn",
"crates/ruvector-gnn-node",
"crates/ruvector-gnn-wasm",
"crates/ruvector-attention",
"crates/ruvector-attention-wasm",
"crates/ruvector-attention-node",
"crates/ruvector-cnn",
"crates/ruvector-cnn-wasm",
"crates/ruvector-mincut",
"crates/ruvector-mincut-wasm",
"crates/ruvector-mincut-node",
"crates/ruvector-mincut-gated-transformer",
"crates/ruvector-mincut-gated-transformer-wasm",
# NOTE: ruvector-postgres is in workspace `exclude` (pgrx env requirement).
"crates/ruvector-nervous-system",
# Iter 219 — hailo backend rejoined the workspace (closes
# ADR-178 Gap E folded into Gap B). All three build clean on
# x86 with default features; opting into the actual NPU path
# requires `--features hailo` on a Pi 5 + AI HAT+.
"crates/hailort-sys",
"crates/ruvector-hailo",
"crates/ruvector-mmwave",
"crates/ruvector-hailo-cluster",
"examples/refrag-pipeline",
"examples/scipix",
"examples/google-cloud",
"examples/subpolynomial-time",
"crates/sona",
"crates/rvlite",
"crates/ruvector-nervous-system",
"crates/ruvector-dag",
"crates/ruvector-dag-wasm",
"crates/ruvector-nervous-system-wasm",
"crates/ruvector-economy-wasm",
"crates/ruvector-learning-wasm",
"crates/ruvector-exotic-wasm",
"crates/ruvector-attention-unified-wasm",
"crates/ruvector-fpga-transformer",
"crates/ruvector-fpga-transformer-wasm",
"crates/ruvector-sparse-inference",
"crates/ruvector-math",
"crates/ruvector-math-wasm",
"examples/benchmarks",
"crates/cognitum-gate-kernel",
"crates/cognitum-gate-tilezero",
"crates/mcp-gate",
"crates/mcp-brain",
"crates/mcp-brain-server",
"crates/ruQu",
"crates/ruvllm",
"crates/ruvllm-cli",
"crates/ruvllm-wasm",
"crates/prime-radiant",
"crates/ruvector-delta-core",
"crates/ruvector-delta-wasm",
"crates/ruvector-delta-index",
"crates/ruvector-delta-graph",
"crates/ruvector-delta-consensus",
"crates/ruvector-crv",
"crates/ruvector-temporal-tensor",
"crates/ruqu-core",
"crates/ruqu-algorithms",
"crates/ruqu-wasm",
"crates/ruqu-exotic",
"crates/ruvector-domain-expansion",
"crates/ruvector-domain-expansion-wasm",
"crates/ruvector-solver",
"crates/ruvector-solver-wasm",
"crates/ruvector-solver-node",
"examples/dna",
"examples/OSpipe",
"crates/ruvector-coherence",
"crates/ruvector-profiler",
"crates/ruvector-attn-mincut",
"crates/ruvector-cognitive-container",
"crates/ruvector-verified",
"crates/ruvector-verified-wasm",
"crates/ruvector-graph-transformer",
"crates/ruvector-graph-transformer-wasm",
"crates/ruvector-graph-transformer-node",
"examples/rvf-kernel-optimized",
"examples/verified-applications",
"crates/thermorust",
"crates/ruvector-dither",
"crates/ruvector-robotics",
"examples/robotics",
"crates/neural-trader-core",
"crates/neural-trader-coherence",
"crates/neural-trader-replay",
"crates/neural-trader-wasm",
# Kalshi integration (ADR-153)
"crates/ruvector-kalshi",
"crates/neural-trader-strategies",
# RuVix Cognition Kernel (organized under crates/ruvix/)
"crates/ruvix/crates/types",
"crates/ruvix/crates/region",
"crates/ruvix/crates/queue",
"crates/ruvix/crates/cap",
"crates/ruvix/crates/proof",
"crates/ruvix/crates/sched",
"crates/ruvix/crates/boot",
"crates/ruvix/crates/vecgraph",
"crates/ruvix/crates/nucleus",
# Phase B: Bare metal AArch64 support
"crates/ruvix/crates/hal",
"crates/ruvix/crates/aarch64",
"crates/ruvix/crates/drivers",
"crates/ruvix/tests",
"crates/ruvix/benches",
"crates/ruvix/examples/cognitive_demo",
# rvAgent — AI Agent Framework (DeepAgents Rust conversion)
"crates/rvAgent/rvagent-core",
"crates/rvAgent/rvagent-backends",
"crates/rvAgent/rvagent-middleware",
"crates/rvAgent/rvagent-tools",
"crates/rvAgent/rvagent-subagents",
"crates/rvAgent/rvagent-cli",
"crates/rvAgent/rvagent-acp",
"crates/rvAgent/rvagent-mcp",
"crates/rvAgent/rvagent-wasm",
"crates/rvAgent/rvagent-a2a",
# ADR-159 a2a-swarm demo
"examples/a2a-swarm",
# ETL pipeline example
"examples/train-discoveries",
# Spectral graph sparsification
"crates/ruvector-sparsifier",
"crates/ruvector-sparsifier-wasm",
# Consciousness metrics (IIT Φ, causal emergence)
"crates/ruvector-consciousness",
"crates/ruvector-consciousness-wasm",
"examples/cmb-consciousness",
"examples/gw-consciousness",
"examples/ecosystem-consciousness",
"examples/quantum-consciousness",
"examples/gene-consciousness",
"examples/climate-consciousness",
# JS bundle decompiler (ADR-135)
"crates/ruvector-decompiler",
"crates/ruvector-decompiler-wasm",
# DiskANN / Vamana (ADR-143)
"crates/ruvector-diskann",
"crates/ruvector-diskann-node",
# Boundary-first scientific discovery PoC
"examples/boundary-discovery",
# CMB Cold Spot boundary-first discovery
"examples/cmb-boundary-discovery",
# FRB population boundary discovery (CHIME-like data)
"examples/frb-boundary-discovery",
# Cosmic void boundary information content
"examples/void-boundary-discovery",
# Multi-regime temporal attractor boundary detection
"examples/temporal-attractor-discovery",
# Music genre boundary discovery via spectral graph bisection
"examples/music-boundary-discovery",
# Weather regime boundary detection (variance/correlation precedes temperature)
"examples/weather-boundary-discovery",
# Market regime boundary discovery via correlation structure
"examples/market-boundary-discovery",
# Health state boundary detection from wearable sensor data
"examples/health-boundary-discovery",
# SETI exotic signals gallery: boundary-first detection of sub-threshold signals
"examples/seti-exotic-signals",
# SETI boundary-first discovery: sub-noise signal detection via coherence graphs
"examples/seti-boundary-discovery",
# Earthquake precursor detection via inter-station correlation boundary shifts
"examples/earthquake-boundary-discovery",
# Pandemic outbreak detection 60 days before case counts via correlation boundaries
"examples/pandemic-boundary-discovery",
# Infrastructure failure prediction via sensor correlation boundaries
"examples/infrastructure-boundary-discovery",
# Pre-seizure detection via brain correlation boundary shifts
"examples/brain-boundary-discovery",
# Clinical-publication-grade pre-seizure detection report with CSV output
"examples/seizure-clinical-report",
# Closed-loop seizure detection + therapeutic response simulation
"examples/seizure-therapeutic-sim",
# Real EEG analysis: CHB-MIT PhysioNet data with boundary-first detection
"examples/real-eeg-analysis",
# Multi-seizure cross-patient analysis: all 7 chb01 seizures
"examples/real-eeg-multi-seizure",
# ruvllm sparse attention kernel for Hailo-10H cluster (ADR-183 ADR-190)
"crates/ruvllm_sparse_attention",
# Generic retrieval LM + masked discrete diffusion built on the kernel
"crates/ruvllm_retrieval_diffusion",
# RAIRS IVF: Redundant Assignment + Amplified Inverse Residual (ADR-193)
"crates/ruvector-rairs",
]
resolver = "2"
[workspace.package]
version = "2.2.3"
edition = "2021"
rust-version = "1.77"
license = "MIT"
authors = ["Ruvector Team"]
repository = "https://github.com/ruvnet/ruvector"
[workspace.dependencies]
# Core functionality
redb = "2.1"
memmap2 = "0.9"
hnsw_rs = "0.3"
simsimd = "5.9"
rayon = "1.10"
crossbeam = "0.8"
# Serialization
rkyv = "0.8"
bincode = { version = "2.0.0-rc.3", features = ["serde"] }
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"
# Node.js bindings
napi = { version = "2.16", default-features = false, features = ["napi9", "async", "tokio_rt"] }
napi-derive = "2.16"
# WASM
wasm-bindgen = "0.2"
wasm-bindgen-futures = "0.4"
js-sys = "0.3"
web-sys = { version = "0.3", features = ["Worker", "MessagePort", "console"] }
getrandom = { version = "0.3", features = ["wasm_js"] }
# Async runtime
tokio = { version = "1.41", features = ["rt-multi-thread", "sync", "macros"] }
futures = "0.3"
# Error handling and utilities
thiserror = "2.0"
anyhow = "1.0"
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
# Math and numerics
nalgebra = { version = "0.33", default-features = false, features = ["std"] }
ndarray = "0.16"
rand = "0.8"
rand_distr = "0.4"
# Time and UUID
chrono = { version = "0.4", features = ["serde"] }
uuid = { version = "1.11", features = ["v4", "serde", "js"] }
# CLI
clap = { version = "4.5", features = ["derive", "cargo"] }
indicatif = "0.17"
console = "0.15"
# Testing and benchmarking
criterion = { version = "0.5", features = ["html_reports"] }
proptest = "1.5"
mockall = "0.13"
# Formal verification
lean-agentic = "=0.1.0"
# Performance
dashmap = "6.1"
parking_lot = "0.12"
once_cell = "1.20"
[profile.release]
opt-level = 3
lto = "fat"
codegen-units = 1
strip = true
panic = "unwind"
[profile.bench]
inherits = "release"
debug = true
[profile.dev]
opt-level = 0
debug = true
[profile.test]
# Patch hnsw_rs to use rand 0.8 instead of 0.9 for WASM compatibility
# This resolves the getrandom version conflict (0.2 vs 0.3)
[patch.crates-io]
hnsw_rs = { path = "./patches/hnsw_rs" }