fix(#41): restore Intel Mac build via ort-dynamic + Homebrew ONNX Runtime (#43)

* fix: restore Intel Mac build via ort-dynamic + system libonnxruntime

Microsoft is discontinuing x86_64 macOS ONNX Runtime prebuilts after
v1.23.0, so ort-sys 2.0.0-rc.11 can't ship an Intel Mac binary and never
will. Previous Intel Mac attempts kept dying in the ort-sys build script
with "does not provide prebuilt binaries for the target x86_64-apple-darwin
with feature set (no features)." Issue #41 was the latest casualty.

Fix: route Intel Mac through the ort-dynamic feature path (runtime dlopen
against a system libonnxruntime installed via Homebrew). This sidesteps
ort-sys prebuilts entirely and works today.

Changes:

- crates/vestige-core/Cargo.toml: split `embeddings` into code-only vs
  backend-choice. The embeddings feature now just pulls fastembed + hf-hub
  + image-models and activates the 27 #[cfg(feature = "embeddings")] gates
  throughout the crate. New `ort-download` feature carries the
  download-binaries-native-tls backend (the historical default). Existing
  `ort-dynamic` feature now transitively enables `embeddings`, so the
  cfg gates stay active when users swap backends.

  Default feature set expands `["embeddings", ...]` -> `["embeddings",
  "ort-download", ...]` so existing consumers see identical behavior.

- crates/vestige-mcp/Cargo.toml: mirrors the split. Adds `ort-download`
  feature that chains to vestige-core/ort-download, keeps `ort-dynamic`
  that chains to vestige-core/ort-dynamic. Both transitively pull
  `embeddings`. Default adds `ort-download` so `cargo install vestige-mcp`
  still picks the prebuilt-ort backend like before.

- .github/workflows/ci.yml: re-adds x86_64-apple-darwin to the
  release-build matrix with `--no-default-features --features
  ort-dynamic,vector-search`. Adds a `brew install onnxruntime` step that
  sets ORT_DYLIB_PATH from `brew --prefix onnxruntime`.

- .github/workflows/release.yml: re-adds x86_64-apple-darwin to the
  release matrix with the same flags + brew install step. The Intel Mac
  tarball now also bundles docs/INSTALL-INTEL-MAC.md so binary consumers
  get the `brew install onnxruntime` + ORT_DYLIB_PATH prereq out of the
  box.

- docs/INSTALL-INTEL-MAC.md: new install guide covering the Homebrew
  prereq, binary install, source build, troubleshooting, and the v2.1
  ort-candle migration plan.

- README.md: replaces the "Intel Mac and Windows build from source only"
  paragraph with the prebuilt Intel Mac install (brew + curl + env var)
  and a link to the full guide. Platform table updated: Intel Mac back
  on the "prebuilt" list.

Verified locally on aarch64-apple-darwin:
- `cargo check --release -p vestige-mcp` -> clean (default features)
- `cargo check --release -p vestige-mcp --no-default-features
   --features ort-dynamic,vector-search` -> clean

Runtime path on Intel Mac (verified on CI):
  brew install onnxruntime
  export ORT_DYLIB_PATH=$(brew --prefix onnxruntime)/lib/libonnxruntime.dylib
  vestige-mcp --version

Fixes #41. Long-term plan (v2.1): migrate to ort-candle pure-Rust backend
so no system ONNX Runtime dep is needed on any platform.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(ci): drop unused brew install + ORT_DYLIB_PATH from CI steps

Build is a cross-compile (macos-latest runner is Apple Silicon targeting
x86_64-apple-darwin) and ort-load-dynamic doesn't link libonnxruntime at
build time — only at runtime via dlopen. So the brew install step and
ORT_DYLIB_PATH export were ceremony without payload. Removed to cut CI
time. Runtime setup remains documented in docs/INSTALL-INTEL-MAC.md for
end users installing the tarball on their own Intel Mac.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ci: run release-build on PRs too — catch Intel Mac regressions pre-merge

Previously release-build was gated behind `github.ref == 'refs/heads/main'`,
so the Intel Mac, aarch64-apple-darwin, and Linux release targets were only
validated AFTER merge to main. If someone broke the Intel Mac cross-compile
by touching feature flags or Cargo dependencies, we'd only find out when
the release tag was cut and the job exploded on main. Extending the guard
to also fire on pull_request means regressions surface in the PR status
check instead of on a release branch.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Sam Valladares 2026-04-23 02:03:45 -05:00 committed by GitHub
parent d3a2274778
commit 5b993e841f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 149 additions and 30 deletions

View file

@ -11,29 +11,41 @@ keywords = ["memory", "spaced-repetition", "fsrs", "embeddings", "knowledge-grap
categories = ["science", "database"]
[features]
default = ["embeddings", "vector-search", "bundled-sqlite"]
default = ["embeddings", "ort-download", "vector-search", "bundled-sqlite"]
# SQLite backend (default, unencrypted)
bundled-sqlite = ["rusqlite/bundled"]
# Encrypted SQLite via SQLCipher (mutually exclusive with bundled-sqlite)
# Use: --no-default-features --features encryption,embeddings,vector-search
# Use: --no-default-features --features encryption,embeddings,ort-download,vector-search
# Set VESTIGE_ENCRYPTION_KEY env var to enable encryption
encryption = ["rusqlite/bundled-sqlcipher"]
# Core embeddings with fastembed (ONNX-based, local inference)
# Downloads a pre-built ONNX Runtime binary at build time (requires glibc >= 2.38)
embeddings = ["dep:fastembed", "fastembed/ort-download-binaries-native-tls"]
# Embedding code paths (fastembed dep, hf-hub, image-models). This feature
# enables the #[cfg(feature = "embeddings")] gates throughout the crate but
# does NOT pick an ort backend. Pair with EXACTLY ONE of `ort-download`
# (prebuilt ONNX Runtime, default) or `ort-dynamic` (runtime-linked system
# libonnxruntime, required on targets without prebuilts).
embeddings = ["dep:fastembed", "fastembed/hf-hub-native-tls", "fastembed/image-models"]
# Default ort backend: ort-sys downloads prebuilt ONNX Runtime at build time.
# Requires glibc >= 2.38. Fails on x86_64-apple-darwin (Microsoft is
# discontinuing Intel Mac prebuilts after ONNX Runtime v1.23.0).
ort-download = ["embeddings", "fastembed/ort-download-binaries-native-tls"]
# HNSW vector search with USearch (20x faster than FAISS)
vector-search = ["dep:usearch"]
# Use runtime-loaded ORT instead of the downloaded pre-built binary.
# Required on systems with glibc < 2.38 (Ubuntu 22.04, Debian 12, RHEL/Rocky 9).
# Mutually exclusive with the default `embeddings` feature's download strategy.
# Usage: --no-default-features --features ort-dynamic,vector-search,bundled-sqlite
# Runtime requirement: libonnxruntime.so must be on LD_LIBRARY_PATH or ORT_DYLIB_PATH set.
ort-dynamic = ["dep:fastembed", "fastembed/ort-load-dynamic", "fastembed/hf-hub-native-tls", "fastembed/image-models"]
# Alternative ort backend: runtime-linked against a system libonnxruntime via
# dlopen. Required on Intel Mac and on systems with glibc < 2.38 (Ubuntu
# 22.04, Debian 12, RHEL/Rocky 9). Transitively enables `embeddings` so the
# #[cfg] gates stay active.
#
# Usage: cargo build --no-default-features \
# --features ort-dynamic,vector-search,bundled-sqlite
# Runtime: export ORT_DYLIB_PATH=/path/to/libonnxruntime.{dylib,so}
# (e.g. $(brew --prefix onnxruntime)/lib/libonnxruntime.dylib)
ort-dynamic = ["embeddings", "fastembed/ort-load-dynamic"]
# Nomic Embed Text v2 MoE (475M params, 305M active, Candle backend)
# Requires: fastembed with nomic-v2-moe feature

View file

@ -10,12 +10,17 @@ categories = ["command-line-utilities", "database"]
repository = "https://github.com/samvallad33/vestige"
[features]
default = ["embeddings", "vector-search"]
default = ["embeddings", "ort-download", "vector-search"]
embeddings = ["vestige-core/embeddings"]
vector-search = ["vestige-core/vector-search"]
# For systems with glibc < 2.38 — use runtime-loaded ORT instead of the downloaded pre-built binary.
# Usage: cargo install --path crates/vestige-mcp --no-default-features --features ort-dynamic,vector-search
ort-dynamic = ["vestige-core/ort-dynamic"]
# Default ort backend: downloads prebuilt ONNX Runtime at build time.
# Fails on targets without prebuilts (notably x86_64-apple-darwin).
ort-download = ["embeddings", "vestige-core/ort-download"]
# Alternative ort backend: runtime-linked system libonnxruntime via dlopen.
# Required on Intel Mac and on systems with glibc < 2.38.
# Usage: cargo build --no-default-features --features ort-dynamic,vector-search
# Runtime: export ORT_DYLIB_PATH=$(brew --prefix onnxruntime)/lib/libonnxruntime.dylib
ort-dynamic = ["embeddings", "vestige-core/ort-dynamic"]
[[bin]]
name = "vestige-mcp"