fix(build-infra): cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP across 6 crates

Per pearl_build_rs_rerun_if_env_changed, every std::env::var() must be
paired with cargo:rerun-if-env-changed. Task #321 fixed crates/ml/build.rs
(commit e3d082968) but missed 6 sibling build.rs files. Each reads
CUDA_COMPUTE_CAP without registering the rerun directive, so cargo
sees no env-change between e.g. SM 89 (L40S) → SM 90 (H100) workflow
re-submissions and cache-hits the wrong-arch cubin from the previous
run. At runtime, the H100 fails to load the SM 89 cubin with
CUDA_ERROR_NO_BINARY_FOR_GPU on rmsnorm — exactly what killed
train-multi-seed-vlv8c (commit 0371d6a76, post-Class-B chain).

Files (all add `println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP")`
just before the env::var() read):
- crates/ml-dqn/build.rs (rmsnorm — root cause of vlv8c failure)
- crates/ml-ensemble/build.rs
- crates/ml-explainability/build.rs
- crates/ml-ppo/build.rs
- crates/ml-supervised/build.rs
- crates/ml-core/build.rs

Atomic single commit per feedback_no_partial_refactor.

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

crates/ml-core/build.rs

@@ -29,6 +29,7 @@ fn main() {
     println!("cargo:rerun-if-changed={}", common_header_path.display());
 
     // Detect GPU architecture from env or default to sm_80
+    println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP");
     let cuda_compute_cap = std::env::var("CUDA_COMPUTE_CAP").unwrap_or_else(|_| "80".to_string());
     let arch = format!("sm_{cuda_compute_cap}");
 

crates/ml-dqn/build.rs

@@ -21,7 +21,13 @@ fn main() {
 
     println!("cargo:rerun-if-changed={}", common_header_path.display());
 
-    // Detect GPU architecture from env or default to sm_80
+    // Detect GPU architecture from env or default to sm_80.
+    // CRITICAL: pair env::var() with rerun-if-env-changed per
+    // pearl_build_rs_rerun_if_env_changed, otherwise sccache + cubin caches
+    // hit-on-SHA across arch changes (e.g., SM 89 L40S → SM 90 H100), and
+    // training fails at runtime with CUDA_ERROR_NO_BINARY_FOR_GPU on rmsnorm
+    // cubin load (commit 0371d6a76 on H100, post-Class-B chain).
+    println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP");
     let cuda_compute_cap = std::env::var("CUDA_COMPUTE_CAP").unwrap_or_else(|_| "80".to_string());
     let arch = format!("sm_{cuda_compute_cap}");
 

crates/ml-ensemble/build.rs

@@ -13,6 +13,7 @@ fn main() {
     let kernel_dir = Path::new("src");
 
     // Detect GPU architecture from env or default to sm_80
+    println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP");
     let cuda_compute_cap = std::env::var("CUDA_COMPUTE_CAP").unwrap_or_else(|_| "80".to_string());
     let arch = format!("sm_{cuda_compute_cap}");
 

crates/ml-explainability/build.rs

@@ -13,6 +13,7 @@ fn main() {
     let kernel_dir = Path::new("src");
 
     // Detect GPU architecture from env or default to sm_80 (matches crates/ml/build.rs).
+    println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP");
     let cuda_compute_cap = std::env::var("CUDA_COMPUTE_CAP").unwrap_or_else(|_| "80".to_string());
     let arch = format!("sm_{cuda_compute_cap}");
 

crates/ml-ppo/build.rs

@@ -29,6 +29,7 @@ fn main() {
     println!("cargo:rerun-if-changed={}", common_header_path.display());
 
     // Detect GPU architecture from env or default to sm_80
+    println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP");
     let cuda_compute_cap = std::env::var("CUDA_COMPUTE_CAP").unwrap_or_else(|_| "80".to_string());
     let arch = format!("sm_{cuda_compute_cap}");
 

crates/ml-supervised/build.rs

@@ -25,6 +25,7 @@ fn main() {
     let manifest_dir = PathBuf::from(std::env::var("CARGO_MANIFEST_DIR").unwrap());
 
     // Detect GPU architecture from env or default to sm_80 (L40S / A100).
+    println!("cargo:rerun-if-env-changed=CUDA_COMPUTE_CAP");
     let cuda_compute_cap = std::env::var("CUDA_COMPUTE_CAP").unwrap_or_else(|_| "80".to_string());
     let arch = format!("sm_{cuda_compute_cap}");