Cargo.toml

[package]
name = "open-ontologies"
version = "2.1.0"
edition = "2024"
description = "AI-native ontology engine: an MCP server and CLI for building, validating, querying and reasoning over RDF and OWL, with a native SHIQ tableaux reasoner, SHACL validation and SPARQL. Single binary, no JVM."
license = "MIT"
repository = "https://github.com/fabio-rovai/open-ontologies"
homepage = "https://github.com/fabio-rovai/open-ontologies"
documentation = "https://docs.rs/open-ontologies"
readme = "README.md"
keywords = ["ontology", "owl", "rdf", "sparql", "mcp"]
categories = ["command-line-utilities", "data-structures", "science"]
# Without this, `cargo package` walks the whole tree. benchmark/ alone is 23GB
# against a 10MB crates.io limit, and studio/ and case-studies/ add another
# 5.5GB. Only what is needed to build and read the crate ships.
#
# Patterns are gitignore-style, so a bare `README.md` matches at every depth
# and pulled in every node_modules readme under studio/. Leading slashes anchor
# them to the package root.
include = [
    "/src/**/*.rs",
    "/Cargo.toml",
    "/README.md",
    "/LICENSE",
    "/CHANGELOG.md",
    "/SECURITY.md",
]

[[bin]]
name = "open-ontologies"
path = "src/main.rs"

[dependencies]
# `is_daemon_alive` runs on every proxy-able invocation; a bare kill(pid, 0)
# avoids forking /bin/kill on the daemon's own hot path.
libc = "0.2"
rmcp = { version = "1.4", features = ["server", "transport-io", "transport-streamable-http-server"] }
axum = "0.8"
tower-http = { version = "0.6", features = ["cors"] }
tokio-util = "0.7"
tokio = { version = "1", features = ["full"] }
oxigraph = "0.5"
rusqlite = { version = "0.32", features = ["bundled"] }
reqwest = { version = "0.12", features = ["json"] }
schemars = "1"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
toml = "0.8"
clap = { version = "4", features = ["derive", "env"] }
tracing = "0.1"
tracing-subscriber = { version = "0.3", features = ["env-filter", "json"] }
chrono = "0.4"
anyhow = "1"
thiserror = "2"
rayon = "1.10"
csv = "1"
quick-xml = { version = "0.37", features = ["serialize"] }
serde_yaml = "0.9"
calamine = { version = "0.30", features = ["dates"] }
arrow = { version = "54", default-features = false, features = ["csv", "json"] }
parquet = { version = "54", default-features = false, features = ["arrow"] }
sqlx = { version = "0.8", default-features = false, features = ["runtime-tokio", "postgres"], optional = true }
duckdb = { version = "1", optional = true, features = ["bundled"] }
tract-onnx = { version = "0.22", optional = true }
tokenizers = { version = "0.21", optional = true, default-features = false, features = ["onig"] }
instant-distance = { version = "0.6", optional = true, features = ["with-serde"] }
bincode = { version = "1.3", optional = true }
sha2 = "0.10"
dirs = "6"
wasmi = { version = "1.1.0", optional = true }
turbovec = { version = "1.0.0", default-features = false, optional = true }

[features]
default = []
postgres = ["sqlx"]
duckdb = ["dep:duckdb"]
sql = ["postgres", "duckdb"]
embeddings = ["tract-onnx", "tokenizers", "instant-distance", "bincode"]
# Causal layer (#48): subprocess wrapper around PyWhy/DoWhy for backdoor
# identification + adjustment estimation. Caller must have `python3` on PATH
# and `pip install dowhy networkx pandas numpy`. The wrapper degrades to a
# clean `pywhy_unavailable` error when imports fail; CIVeX falls back to the
# structural proxy. Zero additional Rust dependencies — the entire feature
# is shipped as embedded Python + subprocess plumbing.
causal-pywhy = []
# WASM plugin host: community tools compiled to wasm32-unknown-unknown, run
# in-process behind onto_plugin_list / onto_plugin_call. Pure-Rust interpreter
# (wasmi) with fuel metering — no system deps, the binary stays self-contained.
plugins = ["dep:wasmi"]
# TurboQuant-backed cosine index (Google Research arXiv:2504.19874) as an
# alternative to the immutable instant-distance HNSW graph. Two properties the
# HNSW index cannot offer: incremental add/remove without a full rebuild, and
# 2-4 bit quantised storage. Implies `embeddings` because it replaces one of
# that feature's two index backends; the Poincare index stays on
# instant-distance (TurboQuant scores inner products, and hyperbolic distance
# is not an inner product on the ambient coordinates).
turbovec = ["dep:turbovec", "embeddings"]

[lints.rust]
# `cfg(kani)` is set by the Kani model checker's own compiler driver, never by
# cargo, so an ordinary build has no way to know the name is real and warns that
# the `#[cfg(kani)]` harnesses in `src/reason.rs` are a typo. Declaring it here
# says the name is expected; it does not enable anything.
unexpected_cfgs = { level = "warn", check-cfg = ['cfg(kani)'] }

[dev-dependencies]
tempfile = "3"
wat = "1.256.0"
# Already a normal dependency; repeated here so a test can assert that a
# `config.toml` section really does carry the key it claims to. A setting that
# only a setter can move is not a setting, and two reasoner budgets were in that
# position. No new crate enters the tree.
toml = "0.8"
# Property testing for the certificate boundary (docs/trusted-computing-base.md).
# The Lean proofs are conditional on the Rust writing down the truth, and that
# boundary is a tab-separated format carrying arbitrary RDF terms: exactly the
# shape where a hand-written example passes and an adversarial one forges a
# derivation. DEV-ONLY on purpose. The shipped binary's dependency surface does
# not grow by a single crate.
proptest = "1"

# A patched Oxigraph, pinned by revision. Two changes over 0.5.9, on branch
# `oo/lexical-forms-0.5.9` of the fork.
#
# 1. `Store::snapshot`, not in Oxigraph 0.5.9. It is a read view pinned to one
#    state that takes no lock, and decision 0010 explains at length why neither
#    thing the unpatched crate offers will do: a transaction pins the state but
#    stops every writer for the length of a reasoning run on the memory backend,
#    and copying the graph costs about 221 bytes a triple. The patch is a public
#    wrapper over `Storage::snapshot`, which `Store::len` and
#    `Store::quads_for_pattern` already call internally on every read.
# 2. A literal is kept as written (oxigraph/oxigraph#2010, fixing #1989; here
#    #335). 0.5.9 stored every literal of an XSD datatype with a value encoding
#    by value and gave it back in the canonical form of the primitive type, so
#    "4.0"^^xsd:decimal came back as "4", "1"^^xsd:boolean as "true",
#    "5"^^xsd:int as "5"^^xsd:integer, and "4.0" and "4" loaded as one triple.
#    A literal is now value-encoded only when decoding gives back the same
#    datatype and lexical form; any other takes the generic typed-literal path.
#
# Pinned by REVISION and not by branch, so that what CI builds is what was
# reviewed. Upstream at oxigraph/oxigraph; when both land this stanza goes and
# the version bound below is all that remains.
[patch.crates-io]
oxigraph = { git = "https://github.com/fabio-rovai/oxigraph.git", rev = "6409fa1c8ad5880399d0ca69b38e43cbb2052ad7" }