Add degradation experiments: one-parameter-at-a-time ablations

Controlled study of how the model degrades. Four variants, each = v1 with a
single field replaced (dataclasses.replace), so differences are attributable:
- small: capacity down (2L/64d, ~0.38M params)
- short: training time down (max_iters 20k->2k)
- ctx:   context window down (256->64)
- data:  data quantity down (max_train_tokens->1M; new TrainConfig knob + train.py slice)

- scripts/compare.py: sample same prompt across all trained configs with a
  shared seed, print side by side, write reports/compare.md
- tests/test_configs.py: enforces one-parameter-at-a-time (only intended fields
  differ from v1) + small param count (3 tests). Full suite: 29 passing.

scripts/compare.py

@@ -0,0 +1,90 @@
+"""Compare generated text across the degradation experiments.
+
+Samples the same prompt(s) from every config that has a trained checkpoint,
+using the same RNG seed for each so differences reflect the model, not sampling
+luck. Prints the results side by side and writes reports/compare.md.
+
+Usage:
+    python scripts/compare.py                              # default prompt, all configs
+    python scripts/compare.py --prompt "The dog and the cat"
+    python scripts/compare.py --suite                      # every suite prompt
+    python scripts/compare.py --configs v1,small,ctx       # a subset
+"""
+
+import argparse
+import sys
+from pathlib import Path
+
+import torch
+
+ROOT = Path(__file__).resolve().parent.parent
+sys.path.insert(0, str(ROOT / "src"))
+
+from sample import (  # noqa: E402
+    SUITE_PROMPTS,
+    TOK_PATH,
+    load_model,
+    pick_device,
+    sample_text,
+)
+from tokenizer import BPETokenizer  # noqa: E402
+
+# Baseline first, then the four one-parameter degradations.
+DEFAULT_CONFIGS = ["v1", "small", "short", "ctx", "data"]
+
+LABELS = {
+    "v1": "v1 (baseline)",
+    "small": "small (less capacity)",
+    "short": "short (less training)",
+    "ctx": "ctx (smaller context)",
+    "data": "data (less data)",
+}
+
+
+def main() -> None:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--configs", default=",".join(DEFAULT_CONFIGS))
+    ap.add_argument("--prompt", default="Once upon a time,")
+    ap.add_argument("--suite", action="store_true")
+    ap.add_argument("--max-new-tokens", type=int, default=200)
+    ap.add_argument("--temperature", type=float, default=0.8)
+    ap.add_argument("--top-k", type=int, default=200)
+    ap.add_argument("--seed", type=int, default=1234)
+    args = ap.parse_args()
+
+    configs = [c.strip() for c in args.configs.split(",") if c.strip()]
+    prompts = SUITE_PROMPTS if args.suite else [args.prompt]
+
+    device = pick_device()
+    tok = BPETokenizer.load(TOK_PATH)
+
+    # Load each available model once; warn about any not yet trained.
+    models = {}
+    for name in configs:
+        if (ROOT / "checkpoints" / name / "ckpt.pt").exists():
+            models[name] = load_model(name, device)
+        else:
+            print(f"[skip {name}: no checkpoint — train it first]")
+    if not models:
+        sys.exit("no trained checkpoints found among: " + ", ".join(configs))
+
+    out = ["# Degradation comparison", ""]
+    for prompt in prompts:
+        print(f"\n########## prompt: {prompt!r} ##########")
+        out += [f"## Prompt: {prompt}", ""]
+        for name, model in models.items():
+            torch.manual_seed(args.seed)  # same RNG state per model = fair compare
+            text = sample_text(model, tok, prompt, device,
+                               args.max_new_tokens, args.temperature, args.top_k)
+            label = LABELS.get(name, name)
+            print(f"\n----- {label} -----\n{text}")
+            out += [f"### {label}", "", f"> {text}", ""]
+
+    out_path = ROOT / "reports" / "compare.md"
+    out_path.parent.mkdir(exist_ok=True)
+    out_path.write_text("\n".join(out))
+    print(f"\nsaved {out_path}")
+
+
+if __name__ == "__main__":
+    main()