mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
3ccdad6c67
## Description On Windows, headroom's Rust core resolves `onnxruntime.dll` at runtime via `ort-load-dynamic`. Without an explicit `ORT_DYLIB_PATH`, the bare DLL search can land on `C:\Windows\System32\onnxruntime.dll`, the Windows ML OS component, and `Session::new()` can deadlock instead of returning an error. Since a hang is not an `Err`, the tiered fallback cannot engage until the proxy-level timeout fires. This PR pins `ORT_DYLIB_PATH` to the pip-installed `onnxruntime` DLL at import time, and wires Rust `tracing` events into Python logging so the proxy log surfaces these failures when they occur. Closes #928 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [x] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - Added `headroom/_ort.py` with a Windows-only, idempotent `ensure_ort_dylib_pinned()` resolver that respects an existing `ORT_DYLIB_PATH`. - Call the pin from `headroom/__init__.py` before importing `_core` consumers. - Log the effective ORT dylib path from the content router startup path on Windows. - Enable Rust tracing-to-log compatibility and initialize `pyo3-log` in the `_core` module. - Add timeout diagnostics in the Magika detector with the effective `ORT_DYLIB_PATH`. - Document `ORT_DYLIB_PATH` and `HEADROOM_MAGIKA_INIT_TIMEOUT_SECS`. - Add unit coverage for the resolver behavior. ## Testing - [x] Unit tests pass (`python -m pytest tests/test_transforms/test_ort_dylib.py -q`) - [x] Linting passes (`ruff check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py`) - [x] Formatting passes (`ruff format --check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text $ python -m pytest tests/test_transforms/test_ort_dylib.py -q 7 passed in 0.19s $ ruff check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py All checks passed! $ ruff format --check headroom/_ort.py headroom/__init__.py headroom/transforms/content_router.py tests/test_transforms/test_ort_dylib.py 4 files already formatted $ cargo check -p headroom-py cargo: The term 'cargo' is not recognized as a name of a cmdlet, function, script file, or executable program. ``` ## Real Behavior Proof - Environment: Windows 11 24H2, Python 3.13, RTX 4080 - Exact command / steps: `python -c "import headroom; from headroom._core import detect_content_type as d; print(d(open('headroom/compress.py').read()).content_type)"` - Observed result: `source_code` in 301ms, clean exit, `Magika: ENABLED` in proxy log - Not tested: macOS/Linux manual runtime behavior; `_ort.py` is a no-op outside Windows, and CI covers cross-platform build/test behavior. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have commented my code, particularly in hard-to-understand areas - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] New and existing unit tests pass locally with my changes - [ ] I have updated the CHANGELOG.md if applicable (N/A: repo uses release-please) ## Additional Notes The branch was rebased onto current `main` and the commit subject was updated to satisfy commitlint. Local Rust verification could not be run on this Windows machine because `cargo` is not installed; GitHub CI should be treated as the Rust build verification for the `pyo3-log` dependency and workspace lockfile changes. --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
128 lines
6.1 KiB
TOML
128 lines
6.1 KiB
TOML
[workspace]
|
||
resolver = "2"
|
||
members = [
|
||
"crates/headroom-core",
|
||
"crates/headroom-proxy",
|
||
"crates/headroom-py",
|
||
"crates/headroom-parity",
|
||
]
|
||
# headroom-py is a Python extension module — it must be built via maturin, not
|
||
# plain cargo (the "extension-module" feature tells pyo3 not to link libpython,
|
||
# which is required for `import` to work). `cargo build --workspace` without
|
||
# explicit members skips it; `cargo test --workspace` still runs its tests
|
||
# because pyo3 can dynamically link here for the cdylib used by tests.
|
||
default-members = [
|
||
"crates/headroom-core",
|
||
"crates/headroom-proxy",
|
||
"crates/headroom-parity",
|
||
]
|
||
|
||
[workspace.package]
|
||
edition = "2021"
|
||
rust-version = "1.80"
|
||
license = "Apache-2.0"
|
||
repository = "https://github.com/chopratejas/headroom"
|
||
authors = ["Headroom Maintainers"]
|
||
|
||
[workspace.dependencies]
|
||
serde = { version = "1", features = ["derive"] }
|
||
# `preserve_order` makes `serde_json::Value::Object` use IndexMap so JSON
|
||
# parse order is preserved through Value→string→Value round-trips. The
|
||
# smart_crusher port relies on this to match Python's `str(dict)` output,
|
||
# which preserves insertion order; otherwise BTreeMap's sorted-key default
|
||
# would diverge from Python on every multi-key object.
|
||
#
|
||
# `arbitrary_precision` keeps the literal numeric token from the source
|
||
# JSON intact: `Value::Number` becomes a wrapper around the original
|
||
# digit string, so `1.0` does NOT collapse to `1`, and `12345678901234567`
|
||
# does NOT lose precision through f64. Required by Realignment invariant
|
||
# I1 (byte-faithful passthrough on unmutated bytes; see REALIGNMENT/02-
|
||
# architecture.md §2.2) and PR-A4 (see REALIGNMENT/03-phase-A-lockdown.md).
|
||
#
|
||
# `raw_value` exposes `serde_json::value::RawValue`, the unparsed JSON
|
||
# fragment type. Phase B PR-B2 uses this to forward unmodified
|
||
# `messages[*]` entries as exact byte copies — the parser captures the
|
||
# original byte slice, so byte-for-byte round-trips work even with
|
||
# whitespace, key order, or escape preferences the producer chose.
|
||
# Enabled here in Phase A so PR-B2 can land as a pure consumer change.
|
||
serde_json = { version = "1", features = ["preserve_order", "arbitrary_precision", "raw_value"] }
|
||
bytes = "1"
|
||
thiserror = "1"
|
||
# `log` compat: when no tracing subscriber is active (the case inside the
|
||
# headroom-py cdylib), events are re-emitted as `log` records so pyo3-log
|
||
# can forward them to Python's logging. No effect on binaries that install
|
||
# a real subscriber.
|
||
tracing = { version = "0.1", features = ["log"] }
|
||
anyhow = "1"
|
||
clap = { version = "4", features = ["derive"] }
|
||
tokio = { version = "1", features = ["macros", "rt-multi-thread", "signal"] }
|
||
axum = "0.7"
|
||
tower = "0.5"
|
||
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls"] }
|
||
pyo3 = { version = "0.24", features = ["abi3-py310"] }
|
||
# Forwards Rust `log` records (incl. tracing events via the `log` compat
|
||
# feature above) into Python's `logging` inside the _core extension module.
|
||
pyo3-log = "0.12"
|
||
# Phase D PR-D1: AWS SigV4 signing for native Bedrock InvokeModel route.
|
||
# `aws-sigv4` provides the canonical-request + signing-key implementation;
|
||
# `aws-config` resolves credentials from the standard provider chain
|
||
# (env vars, profiles, IMDS, ECS task role, etc); `aws-credential-types`
|
||
# exposes `Credentials` so the signer accepts whatever the chain returned.
|
||
aws-sigv4 = { version = "1", default-features = false, features = ["sign-http", "http1"] }
|
||
aws-config = { version = "1", default-features = false, features = ["behavior-version-latest", "rustls", "rt-tokio", "sso"] }
|
||
aws-credential-types = { version = "1", default-features = false }
|
||
# `Identity` lives in aws-smithy-runtime-api; the SigV4 builder
|
||
# accepts `&Identity`. Pinning the version explicitly avoids a
|
||
# silent semver bump from the transitive dep tree.
|
||
aws-smithy-runtime-api = { version = "1", default-features = false, features = ["client"] }
|
||
# PR-D4: Vertex publisher path uses GCP Application Default Credentials
|
||
# (ADC) → bearer token for the `Authorization: Bearer <token>` header.
|
||
# `gcp_auth` resolves the chain (gcloud user creds, GCE/GKE metadata
|
||
# server, service-account JSON, workload-identity federation) without
|
||
# us baking provider-specific knowledge in. The token source is wrapped
|
||
# in a `TokenSource` trait so tests inject a static-token mock.
|
||
gcp_auth = "0.12"
|
||
|
||
|
||
# ── Release profile — wheel size optimization ───────────────────────
|
||
#
|
||
# PyPI imposes a 10 GB cumulative storage limit per project. We hit it
|
||
# at version 0.21.36 (191 versions × ~213 MB/release = 10.00 GB
|
||
# exactly). Recent wheels were ~16-18 MB each, of which ~6.4 MB was
|
||
# pure debug metadata (`.strtab` + `.symtab` ELF sections; uncovered
|
||
# by post-mortem inspection of an actual production wheel).
|
||
#
|
||
# This profile shrinks each Linux wheel from ~18 MB → ~10-11 MB by:
|
||
# * Stripping symbol/string tables (~6.4 MB direct savings)
|
||
# * Link-time optimization across crate boundaries (~5-10% .text
|
||
# savings via dead-code elim across the workspace)
|
||
# * Single codegen unit (better inlining + dead-code elim, at the
|
||
# cost of slightly slower release builds)
|
||
#
|
||
# We deliberately do NOT set ``panic = "abort"``. The proxy is a
|
||
# long-lived async process — a single misbehaving request triggering
|
||
# panic-abort would terminate the whole proxy and disconnect every
|
||
# concurrent client. Accept the smaller savings; keep unwind behaviour.
|
||
#
|
||
# Estimated impact: 213 MB/release → ~130 MB/release. Buys ~30+ more
|
||
# release slots within the 10 GB ceiling at the current release
|
||
# cadence. Per-PyPI-version savings AND faster downloads for end
|
||
# users. Tradeoff: release builds take ~30-50% longer due to
|
||
# `codegen-units = 1` + LTO; acceptable for the size win.
|
||
[profile.release]
|
||
strip = "symbols"
|
||
lto = "thin"
|
||
codegen-units = 1
|
||
|
||
# Fast-to-compile profile for CI test wheels. The shipped wheel uses
|
||
# `release` (lto + codegen-units=1) for runtime/size; CI only needs a working
|
||
# extension, so trade runtime perf for ~parallel, lto-free compilation. Used
|
||
# via `maturin build --profile ci`. Does NOT affect `--release` builds.
|
||
[profile.ci]
|
||
inherits = "release"
|
||
lto = false
|
||
codegen-units = 256
|
||
opt-level = 1
|
||
strip = "none"
|
||
debug = false
|
||
incremental = false
|