Lumotia/crates/transcription/build.rs

//! Build-time guard for item #6 of the Whisper ecosystem pass.
//!
//! On Windows, linking `whisper-rs-sys` (MSVC C++ runtime) and the
//! `tokenizers` crate (which pulls a different MSVC CRT via its
//! onnxruntime + Rust-side dependencies) in the same binary has been a
//! repeated failure mode — most recently Whispering v7.11.0 shipped a
//! broken Windows build over exactly this conflict. Reference:
//! https://github.com/EpicenterHQ/epicenter/releases/tag/v7.11.0
//!
//! The easiest defence is to refuse to compile at all if any part of the
//! workspace ever pulls `tokenizers` into the dependency graph on a
//! Windows target. If we ever legitimately need it we can reintroduce
//! it via a sidecar (isolated process, separate CRT) rather than
//! linking it into `lumotia_lib`.
//!
//! The check is advisory on non-Windows targets — it still prints a
//! cargo:warning if `tokenizers` appears, so the Windows failure isn't
//! a surprise at CI time when we build cross-platform from Linux.

use std::env;
use std::fs;
use std::path::PathBuf;

fn main() {
    println!("cargo:rerun-if-changed=build.rs");

    let target_os = env::var("CARGO_CFG_TARGET_OS").unwrap_or_default();
    let manifest_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR").unwrap_or_else(|_| ".".into()));

    // Walk up to workspace root: crates/transcription/ -> crates/ -> root
    let workspace_root = manifest_dir
        .ancestors()
        .find(|p| p.join("Cargo.lock").exists())
        .map(PathBuf::from);

    let Some(root) = workspace_root else {
        // No lockfile yet (e.g. first-ever cargo run). Nothing to check.
        return;
    };

    let lock_path = root.join("Cargo.lock");
    println!("cargo:rerun-if-changed={}", lock_path.display());

    let lock = match fs::read_to_string(&lock_path) {
        Ok(s) => s,
        Err(_) => return,
    };

    let has_tokenizers = lock
        .lines()
        .any(|line| matches!(line.trim(), "name = \"tokenizers\""));

    if !has_tokenizers {
        return;
    }

    if target_os == "windows" {
        panic!(
            "lumotia-transcription: the `tokenizers` crate appears in Cargo.lock and this is a \
             Windows build. Linking `whisper-rs-sys` + `tokenizers` in the same binary has \
             been a persistent MSVC C-runtime conflict (see Whispering v7.11.0). Route any \
             tokenizer usage through an out-of-process sidecar instead, or gate it off for \
             Windows. Brief item #6."
        );
    }

    println!(
        "cargo:warning=lumotia-transcription: `tokenizers` crate is in the dependency graph. \
         This build is non-Windows so the link will succeed, but Windows builds will panic \
         at build time per docs/whisper-ecosystem/brief.md item #6. Isolate tokenizer usage \
         in a sidecar before a Windows ship."
    );
}