fix: smoketest max_bars 60K→5K + counterfactual test threshold

- Reduce max_bars from 60000 to 5000 (smoketests ran 16min, now ~1min)
- Fix test_counterfactual_experiences_in_buffer: compute threshold from
  actual config instead of hardcoded 4000, enlarge buffer to avoid wrap

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

config/training/dqn-smoketest.toml

@@ -21,7 +21,7 @@ hidden_dim_base = 64
 reward_scale = 1.0
 huber_delta = 1.0
 symbol = "ES.FUT"
-max_bars = 60000
+max_bars = 5000
 imbalance_bar_threshold = 1.0
 imbalance_bar_ewma_alpha = 0.1
 

crates/ml/src/trainers/dqn/smoke_tests/regression.rs

@@ -161,9 +161,15 @@ fn test_counterfactual_experiences_in_buffer() -> anyhow::Result<()> {
     let mut p = smoke_params();
     p.epochs = 1;
     p.early_stopping_enabled = false;
-    // Ensure we can distinguish 1x from 2x: buffer must be large enough to hold 2x
-    // smoketest defaults: gpu_n_episodes=32, gpu_timesteps=100, buffer_size=10000
-    // base = 32 * 100 = 3200, counterfactual = 6400, fits in 10000
+
+    // Compute expected counts from the actual config
+    let n_ep = p.gpu_n_episodes;
+    let ts = p.gpu_timesteps_per_episode;
+    let base = n_ep * ts;
+    let with_cf = base * 2; // counterfactual doubles
+    // Buffer must be large enough to hold 2x WITHOUT wrapping, so we can
+    // distinguish 1x from 2x by counting entries.
+    p.buffer_size = with_cf + 100;
 
     let mut trainer = smoke_trainer_with(p)?;
     let rt = tokio::runtime::Builder::new_current_thread()
@@ -173,27 +179,24 @@ fn test_counterfactual_experiences_in_buffer() -> anyhow::Result<()> {
         Ok("skip".to_owned())
     }))?;
 
-    // Check replay buffer size via the agent
     let buffer_size = rt.block_on(async {
         let agent = trainer.get_agent().read().await;
         agent.get_replay_buffer_size().unwrap_or(0)
     });
 
-    // With counterfactual: 32 * 100 * 2 = 6400
-    // Without counterfactual (the old bug): 32 * 100 = 3200
-    // Threshold at 4000 cleanly separates the two cases.
-    let min_expected = 4000;
+    // With counterfactual: buffer should have more entries than base (1x).
+    // Threshold: midpoint between 1x and 2x cleanly separates the cases.
+    let min_expected = (base + with_cf) / 2;
     assert!(
         buffer_size >= min_expected,
-        "PER buffer has {} entries (expected >= {min_expected}). \
-         Counterfactual experiences may be silently dropped again. \
-         With gpu_n_episodes=32, timesteps=100, expected 6400 (32*100*2).",
-        buffer_size
+        "PER buffer has {buffer_size} entries (expected >= {min_expected}). \
+         base={base}, with_cf={with_cf}. \
+         Counterfactual experiences may be silently dropped.",
     );
 
     tracing::info!(
-        "Counterfactual regression: PER buffer has {} entries (expected ~6400)",
-        buffer_size
+        "Counterfactual regression: PER buffer has {buffer_size} entries \
+         (expected ~{with_cf}, threshold={min_expected})",
     );
     Ok(())
 }