feat: CLI coding agent bakeoff — 26b reproducibly silent-stops at write_file

Ran minimal agent loop (Ollama /api/chat + read_file/write_file/run_bash) on
steel141 3090 Ti against 3 models on a broken-median-function task:

- gemma4:31b-it-q4_K_M: PASS (8 iters, 1 write, 44s) — textbook trace
- qwen3-coder:30b: PASS (15 iters, 1 write, 22s) — correct but chatty
- gemma4:26b: FAIL (6 iters, 0 writes) — silently stops with eval=4
  after reading source. Reproduced on second run. One-shot probe
  confirms 26b CAN produce the correct fix — failure is specifically
  at the write_file tool-call argument boundary.

Updates GOTCHAS with a new HIGH-severity entry, SYNTHESIS model-selection
table, CORPUS_cli_coding_agent.md empirical-follow-up pointer, and adds
docs/reference/bakeoff-2026-04-18.md with the full writeup.

scripts/bakeoff/task_seed/tests/test_stats.py

@@ -0,0 +1,30 @@
+from calc.stats import mean, median, mode, variance
+
+
+def test_mean_basic():
+    assert mean([1, 2, 3, 4, 5]) == 3.0
+
+
+def test_median_odd():
+    assert median([1, 2, 3]) == 2
+
+
+def test_median_even():
+    assert median([1, 2, 3, 4]) == 2.5
+
+
+def test_median_unsorted():
+    assert median([3, 1, 4, 1, 5, 9, 2, 6]) == 3.5
+
+
+def test_median_floats():
+    assert median([1.0, 2.0, 3.0, 4.0]) == 2.5
+
+
+def test_mode_basic():
+    assert mode([1, 2, 2, 3]) == 2
+
+
+def test_variance_basic():
+    # sample variance (n-1) of [1, 2, 3, 4, 5] is 10/4 = 2.5
+    assert variance([1, 2, 3, 4, 5]) == 2.5