Make config dataclasses the single source of truth for DEFAULT_CONFIG

DEFAULT_CONFIG and build_models/build_critics/StageSpec.from_config's
inline .get(key, default) fallbacks had already drifted: two keys
(stage2_model.decoder, stage2_model.particle_type.target) resolved
differently depending on whether a config dict came from
merge_cli_overrides (fully populated, correct) or was hand-built and
partial (fell back to stale v0.2-shaped literals). Introduce frozen
dataclasses (GiantConfig and its nested blocks) in giant/config.py as
the actual single declaration of every default; DEFAULT_CONFIG is now
generated from them instead of hand-maintained, and build_models,
build_critics, and StageSpec.from_config consume the dataclasses
instead of duplicating literal fallbacks, so this class of drift can't
recur. Router/n_sec sub-blocks keep an `extra` catch-all for their
genuinely dynamic keys (composed-router axes, runtime-seeded
centers_init, legacy_owner).

Fixing the fallback surfaced the same latent bug in two existing
partial-config callers that had been silently depending on it: a
test fixture in test_train.py and scripts/warm_setup_cache.py's
minimal cfg (now merged against DEFAULT_CONFIG instead of hand-rolled,
closing the gap for good). See issues.md Issue 1.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

tests/test_config.py

@@ -27,6 +27,80 @@ def test_conditioning_enum_has_onehot():
     }
 
 
+# ---------------------------------------------------------------------------
+# Config dataclasses (issues.md Issue 1)
+# ---------------------------------------------------------------------------
+
+
+def test_giant_config_to_dict_matches_default_config():
+    """DEFAULT_CONFIG is generated from GiantConfig().to_dict() (not
+    hand-maintained), so the two cannot structurally drift apart — but this
+    pins the *equality* too, catching e.g. a stray in-place mutation of
+    DEFAULT_CONFIG added elsewhere after import."""
+    assert gconfig.GiantConfig().to_dict() == gconfig.DEFAULT_CONFIG
+
+
+@pytest.mark.parametrize(
+    "cls",
+    [
+        gconfig.ConditioningAxisConfig,
+        gconfig.ConditioningConfig,
+        gconfig.FlowConfig,
+        gconfig.DdpmConfig,
+        gconfig.Stage1WganConfig,
+        gconfig.Stage2WganConfig,
+        gconfig.RouterConfig,
+        gconfig.Stage2RouterConfig,
+        gconfig.NSecConfig,
+        gconfig.ParticleTypeConfig,
+        gconfig.AutoregressiveConfig,
+        gconfig.Stage1ModelConfig,
+        gconfig.Stage2ModelConfig,
+        gconfig.TrainConfig,
+        gconfig.GiantConfig,
+    ],
+)
+def test_config_dataclass_from_dict_round_trips_through_to_dict(cls):
+    assert cls.from_dict(cls().to_dict()) == cls()
+    assert cls.from_dict(None) == cls()
+
+
+def test_stage2_model_config_defaults_match_documented_v030_intent():
+    """The two keys issues.md Issue 1 found drifted between DEFAULT_CONFIG
+    and build_models/StageSpec.from_config's own .get(key, default)
+    fallbacks — pinned directly against the dataclass that is now their
+    shared single source of truth."""
+    spec = gconfig.Stage2ModelConfig()
+    assert spec.decoder == "autoregressive"
+    assert spec.particle_type.target == "onehot"
+
+
+def test_router_config_extra_round_trips_composed_axis_keys():
+    d = {"enabled": True, "type": "composed", "axis0_type": "energy", "axis0_n_experts": 4}
+    router = gconfig.RouterConfig.from_dict(d)
+    assert router.enabled is True
+    assert router.extra == {"axis0_type": "energy", "axis0_n_experts": 4}
+    assert router.to_dict()["axis0_type"] == "energy"
+
+
+def test_stage2_router_config_tie_to_stage1_not_leaked_into_extra():
+    router = gconfig.Stage2RouterConfig.from_dict({"tie_to_stage1": True})
+    assert router.tie_to_stage1 is True
+    assert "tie_to_stage1" not in router.extra
+
+
+def test_stage1_router_config_has_no_tie_to_stage1_key():
+    """Stage 1's router schema must not gain stage 2's tie_to_stage1 key —
+    that would change every future run's saved config.toml shape."""
+    assert "tie_to_stage1" not in gconfig.RouterConfig().to_dict()
+
+
+def test_n_sec_config_extra_round_trips_legacy_owner():
+    n_sec = gconfig.NSecConfig.from_dict({"mode": "head", "legacy_owner": "stage1"})
+    assert n_sec.legacy_owner == "stage1"
+    assert n_sec.to_dict() == {"mode": "head", "lambda": 0.1, "legacy_owner": "stage1"}
+
+
 # ---------------------------------------------------------------------------
 # _deep_merge
 # ---------------------------------------------------------------------------