feat(predict): enrich YAML sidecar with provenance and timing

`giant predict`'s sidecar previously stopped at kind/prediction_id/
output/dataset/checkpoint/timestamp, unlike `giant rollout`'s, which
carries full run provenance (model_config, training_epoch,
training_config, timing, ...) that flows into analysis gallery
metadata. `analyze --prediction` consumed the same thin sidecar, so a
prediction series in an analysis run was nearly unlabeled compared to
its rollout counterparts.

- `_write_prediction_ref` takes an `extra: dict | None` merged into
  the sidecar; `giant rollout` now uses it instead of a
  load/update/rewrite round trip (identical output).
- New `_build_predict_timing`, key-compatible with
  `_build_rollout_timing`, from timers now wrapping predict's setup/
  sample/write phases.
- `giant predict` writes coord, has_truth, schema_version, steps,
  weights, device, batch_size(+auto), row/skip/unknown-pdg counts,
  timing, and the checkpoint's model_config/config_overrides/
  training_epoch/best_val_loss/training_config/training_meta.
- `giant/analysis/condor.py`'s `_PLOT_META_KEYS` forwards the new
  predict-only keys (plus rollout's previously-unforwarded
  config_overrides) into each plot's gallery metadata.yaml.
- Fixes a `ty` regression from the prior commit in
  tests/test_cli_predict.py (Command has no static `.commands`).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PpxE9nij3ujg9XcuzvQ26q

tests/test_cli_predict.py

@@ -6,6 +6,7 @@ from typer.testing import CliRunner
 
 from giant.cli import (
     _CEPH_PREDICTIONS,
+    _build_predict_timing,
     _resolve_prediction_output,
     _write_prediction_ref,
     app,
@@ -145,6 +146,46 @@ def test_ref_timestamp_is_iso_format(tmp_path):
     assert ts.tzinfo is not None
 
 
+def test_ref_yaml_merges_extra_after_base_fields(tmp_path):
+    ckpt_dir = tmp_path / "checkpoints"
+    ckpt_dir.mkdir()
+    checkpoint = ckpt_dir / "best.pt"
+    checkpoint.touch()
+
+    out = tmp_path / "pred.parquet"
+    dataset = tmp_path / "full.manifest"
+    pred_uuid = str(uuid.uuid4())
+
+    ref_path = _write_prediction_ref(
+        checkpoint,
+        pred_uuid,
+        out,
+        dataset,
+        extra={"coord": "global", "n_rows": 42, "timing": {"setup_s": 1.0}},
+    )
+    data = yaml.safe_load(ref_path.read_text())
+
+    # Base fields untouched, extras layered on top.
+    assert data["kind"] == "prediction"
+    assert data["prediction_id"] == pred_uuid
+    assert data["coord"] == "global"
+    assert data["n_rows"] == 42
+    assert data["timing"] == {"setup_s": 1.0}
+
+
+def test_ref_yaml_without_extra_matches_today(tmp_path):
+    ckpt_dir = tmp_path / "checkpoints"
+    ckpt_dir.mkdir()
+    checkpoint = ckpt_dir / "best.pt"
+    checkpoint.touch()
+
+    pred_uuid = str(uuid.uuid4())
+    ref_path = _write_prediction_ref(checkpoint, pred_uuid, tmp_path / "p.parquet", tmp_path / "d")
+    data = yaml.safe_load(ref_path.read_text())
+
+    assert set(data) == {"kind", "prediction_id", "output", "dataset", "checkpoint", "timestamp"}
+
+
 def test_ref_checkpoint_path_is_absolute(tmp_path):
     ckpt_dir = tmp_path / "checkpoints"
     ckpt_dir.mkdir()
@@ -232,13 +273,52 @@ def test_predict_truth_metadata_key_exists():
     assert PREDICT_TRUTH_METADATA_KEY == "giant.predict.has_truth"
 
 
+# ---------------------------------------------------------------------------
+# _build_predict_timing
+# ---------------------------------------------------------------------------
+
+
+def test_build_predict_timing_computes_per_step_cost():
+    timing = _build_predict_timing(
+        setup_s=1.0,
+        predict_s=10.0,
+        write_s=2.0,
+        n_rows=100,
+        device="cpu",
+        torch_threads=4,
+    )
+    assert timing["n_rows"] == 100
+    assert timing["sample_s"] == 8.0  # predict_s - write_s
+    assert timing["us_per_step"] == 8.0 / 100 * 1e6
+    assert timing["write_us_per_step"] == 2.0 / 100 * 1e6
+    assert timing["rows_per_s"] == 10.0
+    assert timing["device"] == "cpu" and timing["torch_threads"] == 4
+
+
+def test_build_predict_timing_handles_zero_rows():
+    timing = _build_predict_timing(
+        setup_s=1.0,
+        predict_s=0.0,
+        write_s=0.0,
+        n_rows=0,
+        device="cpu",
+        torch_threads=1,
+    )
+    assert timing["us_per_step"] is None
+    assert timing["write_us_per_step"] is None
+    assert timing["rows_per_s"] is None
+
+
 def test_predict_has_truth_flag_default_on():
     # Inspecting rendered --help text is brittle across terminal
     # widths/color settings (wraps or re-colors mid-flag); go straight to
     # the underlying click command's registered option instead.
-    import typer
+    from typing import cast
 
-    predict_cmd = typer.main.get_command(app).commands["predict"]
+    import typer
+    from click import Group
+
+    predict_cmd = cast(Group, typer.main.get_command(app)).commands["predict"]
     truth_param = next(p for p in predict_cmd.params if p.name == "truth")
     assert truth_param.opts == ["--truth"]
     assert truth_param.secondary_opts == ["--no-truth"]