bench(longmemeval): --float16, and float16 measured on real embeddings

`longmemeval_bench --float16` builds every per-question store with
MemoryConfig::float16, so the vector stage searches half-rounded
embeddings exactly as such a store holds them.

Full longmemeval_s (500 questions, ~494 turns each) with real
all-MiniLM-L6-v2 embeddings, f32 vs float16, on tank (CUDA): identical
at every Hit@k and MRR, turn and session level, in all eight modes —
bar RRF session MRR 0.9253 vs 0.9254 and one or two flips out of ~320
in which gold session ranks first. The f32 run reproduces the published
hybrid numbers exactly. The earlier float16 evidence was synthetic
clustered data only; this is the real-embedding check.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/clawhdf5-bench/src/bin/longmemeval_bench.rs

@@ -64,6 +64,11 @@ use tempfile::TempDir;
 
 const EMBEDDING_DIM: usize = 384;
 
+/// `--float16`: build every per-question store with `MemoryConfig::float16`,
+/// so embeddings are rounded to half precision as they are saved — exactly
+/// what such a store searches over.
+static FLOAT16: std::sync::atomic::AtomicBool = std::sync::atomic::AtomicBool::new(false);
+
 /// A mode's fusion, as one short string for the reports.
 fn describe(mode: Mode) -> String {
     let fusion = match mode.fusion {
@@ -431,6 +436,7 @@ fn evaluate_question(
     let mut config = MemoryConfig::new(dir.path().join("lme.h5"), "lme-bench", EMBEDDING_DIM);
     config.wal_enabled = false;
     config.compact_threshold = 0.0;
+    config.float16 = FLOAT16.load(std::sync::atomic::Ordering::Relaxed);
 
     let mut memory = HDF5Memory::create(config).expect("failed to create HDF5Memory");
     memory.set_token_filter(mode.tokens);
@@ -940,6 +946,10 @@ fn main() {
                 limit = Some(v.parse().expect("--limit must be a positive integer"));
             }
             "--sweep" => sweep = true,
+            "--float16" => {
+                FLOAT16.store(true, std::sync::atomic::Ordering::Relaxed);
+                eprintln!("Stores use MemoryConfig::float16 (half-precision embeddings)");
+            }
             "--rerank-sweep" => {
                 // Re-ranking needs the vector stage to have candidates worth
                 // reordering, so this is an embeddings-only comparison.
@@ -971,6 +981,9 @@ fn main() {
                      --rerank-sweep\n\
                               compare re-ranking off, metadata-only (the old\n\
                               behaviour) and blended at several half-lives.\n\
+                     --float16\n\
+                              build each store with MemoryConfig::float16, to\n\
+                              compare retrieval on half-precision embeddings.\n\
                      --sweep  instead of the three named modes, sweep vector_weight\n\
                               from 0.0 to 1.0 in 0.1 steps. The 0.7/0.3 default was\n\
                               never searched; this is what searches it."