From fb22108c570041f306f9ecbe25c516268a8aaab7 Mon Sep 17 00:00:00 2001
From: Xin Wang <wangx@macmini.com>
Date: Mon, 7 Sep 2026 00:51:14 +0800
Subject: [PATCH] Fix one-epoch track GRU smoke launcher

---
 PROJECT_CONTEXT.md                 |  4 +++-
 docs/easycom_track_gru_residual.md |  8 ++++++++
 run_easycom_track_gru_residual.sh  | 10 +++++++++-
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/PROJECT_CONTEXT.md b/PROJECT_CONTEXT.md
index 8187baa..1b939a9 100644
--- a/PROJECT_CONTEXT.md
+++ b/PROJECT_CONTEXT.md
@@ -62,7 +62,9 @@ result.
 - `track-gru-residual` builds strictly causal histories from anonymous provided
   track IDs, applies one shared GRU per track, lets G+A query current track
   states, and adds a zero-gated correction to an exactly initialized pooled
-  `G+A+V` checkpoint. See
+  `G+A+V` checkpoint. Its three focused loader/head/CLI round-trip tests passed
+  on the remote PyTorch/L20 environment on 2026-09-07; the one-session GPU
+  smoke and measured experiment are still pending. See
   [`docs/easycom_track_gru_residual.md`](docs/easycom_track_gru_residual.md).
 
 ### Current blocker
diff --git a/docs/easycom_track_gru_residual.md b/docs/easycom_track_gru_residual.md
index a8b9ece..483cb30 100644
--- a/docs/easycom_track_gru_residual.md
+++ b/docs/easycom_track_gru_residual.md
@@ -60,6 +60,11 @@ The existing EasyCom local sidecars already contain crop features, frame times,
 source-clip indices and person IDs; this experiment does not require feature
 re-extraction.
 
+Runtime status (2026-09-07): the focused causal-history, exact-zero-gate and
+train/infer round-trip tests passed in 49.699 seconds on the remote PyTorch/L20
+environment. This verifies the code path, not model quality. The one-session
+GPU training smoke and full experiment remain unmeasured.
+
 ## Fair initialization
 
 `track-gru-residual` requires `--initialize-pooled-checkpoint`. The loader
@@ -103,6 +108,9 @@ CUDA_VISIBLE_DEVICES=0 \
 bash run_easycom_track_gru_residual.sh all 0
 ```
 
+For `EPOCHS=1`, the launcher automatically uses zero warmup unless
+`WARMUP_EPOCHS` is explicitly supplied.
+
 Then use three GPUs in three foreground terminals. These runs report Session
 12 development scores, not the official test set:
 
diff --git a/run_easycom_track_gru_residual.sh b/run_easycom_track_gru_residual.sh
index 703cd43..c1f7572 100755
--- a/run_easycom_track_gru_residual.sh
+++ b/run_easycom_track_gru_residual.sh
@@ -11,7 +11,14 @@ CHECKPOINT_ROOT=${CHECKPOINT_ROOT:-checkpoints/easycom_track_gru_residual}
 RESULT_ROOT=${RESULT_ROOT:-results/easycom_track_gru_residual}
 TEST_RESULT_ROOT=${TEST_RESULT_ROOT:-results/easycom_track_gru_residual_test}
 EPOCHS=${EPOCHS:-4}
-WARMUP_EPOCHS=${WARMUP_EPOCHS:-1.6}
+if [[ -z "${WARMUP_EPOCHS:-}" ]]; then
+  # Keep the four-epoch screen unchanged, but make EPOCHS=1 smoke runs valid.
+  if (( EPOCHS == 1 )); then
+    WARMUP_EPOCHS=0
+  else
+    WARMUP_EPOCHS=1.6
+  fi
+fi
 LOCAL_PROJECTION_DIM=${LOCAL_PROJECTION_DIM:-256}
 PERSON_ATTENTION_DIM=${PERSON_ATTENTION_DIM:-256}
 PERSON_ATTENTION_HEADS=${PERSON_ATTENTION_HEADS:-4}
@@ -147,6 +154,7 @@ if [[ "$variant" == test ]]; then
       fi
       if [[ ! -s "$checkpoint" ]]; then
         echo "Missing checkpoint: $checkpoint" >&2
+        echo "The test mode is inference-only; run 'all' for these seeds first." >&2
         exit 1
       fi
       echo "$(date): final test ${selected}, seed=${seed}"