feat(ml): cierre del bucle de mejora comfyui-skill (genera→juzga→bump)

Tres funciones nuevas que cierran el lazo skill→generación→juicio→promoción
del grupo comfyui-skill (issue 0087):

- comfyui_bump_skill_version (impura): promueve una versión nueva SOLO si el
  score del panel-juez sube (gate objetivo). Snapshot versions/vN.json
  pre-mutación, deep-merge de recipe_patch, semver↑, línea en growth_log.jsonl.
  force=True salta el gate. No usa datetime.now().
- comfyui_update_skill_score (impura): media incremental de score_mean/score_n
  reescribiendo recipe.json in-place (sin snapshot ni growth_log).
- comfyui_generate_with_skill_oneshot (pipeline): one-shot load→build→submit→
  wait→fetch→judge→score_mean. recipe_patch prueba variantes sin guardar score.
  Compone 7 funciones del registry.

Tests offline: 11 passed (gate, semver, deep-merge, media incremental, errores).
Página madre docs/capabilities/comfyui-skill.md: +3 funciones, sección "Bucle de
mejora" con diagrama, fronteras de scoring actualizadas.

Demo real verificada: skill seed portrait_cinematic_sd15 (SD1.5) generó imagen
SFW real, el panel la juzgó, una variante puntuó más alto (4.787 > 4.7276) y el
gate promovió v1.0.0→v1.1.0 con el judge_run_id como evidencia.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

python/functions/ml/tests/test_comfyui_bump_skill_version.py

@@ -0,0 +1,127 @@
+"""Tests offline para comfyui_bump_skill_version (impura, sin red/GPU).
+
+Verifican el contrato del bucle de mejora contra una librería temporal:
+- golden: score sube → promueve, snapshot pre-mutación, semver subido, recipe_patch aplicado,
+  growth_log con una línea bien formada,
+- edge: bump major/patch + deep-merge anidado sin pisar otras claves,
+- error: gate (score no mejora sin force) → ok=False; force salta el gate; skill inexistente.
+"""
+
+import json
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(__file__))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
+
+import pytest  # noqa: E402
+
+from ml.comfyui_bump_skill_version import comfyui_bump_skill_version, _bump_semver, _deep_merge  # noqa: E402
+
+
+def _seed_skill(lib, slug="demo_skill", version="1.0.0", **extra):
+    sdir = os.path.join(lib, slug)
+    os.makedirs(os.path.join(sdir, "versions"), exist_ok=True)
+    recipe = {"schema_version": 1, "slug": slug, "version": version,
+              "base_workflow": "txt2img", "checkpoint": "dreamshaper_8.safetensors",
+              "params": {"steps": 28, "cfg": 6.0}, **extra}
+    with open(os.path.join(sdir, "recipe.json"), "w", encoding="utf-8") as f:
+        json.dump(recipe, f)
+    return sdir
+
+
+def test_semver_helper():
+    assert _bump_semver("1.0.0", "minor") == "1.1.0"
+    assert _bump_semver("1.2.3", "major") == "2.0.0"
+    assert _bump_semver("1.2.3", "patch") == "1.2.4"
+    assert _bump_semver("nan", "minor") == "0.1.0"  # versión mal formada → 0.0.0 base
+
+
+def test_deep_merge_no_pisa_otras_claves():
+    base = {"params": {"steps": 28, "cfg": 6.0}, "checkpoint": "a"}
+    out = _deep_merge(base, {"params": {"steps": 32}})
+    assert out == {"params": {"steps": 32, "cfg": 6.0}, "checkpoint": "a"}
+    assert base["params"]["steps"] == 28  # no muta el original
+
+
+def test_golden_promueve_cuando_score_sube(tmp_path):
+    lib = str(tmp_path)
+    _seed_skill(lib)
+    res = comfyui_bump_skill_version(
+        "demo_skill", "subir steps a 32", score_before=6.5, score_after=7.4,
+        judge_run_id="judge_xyz", recipe_patch={"params": {"steps": 32}}, library_dir=lib)
+
+    assert res["ok"] is True
+    assert res["old_version"] == "1.0.0"
+    assert res["new_version"] == "1.1.0"
+
+    # snapshot pre-mutación conserva la receta vieja (steps 28).
+    with open(res["snapshot_file"], encoding="utf-8") as f:
+        snap = json.load(f)
+    assert snap["params"]["steps"] == 28
+    assert snap["version"] == "1.0.0"
+
+    # recipe.json mutado: patch aplicado + semver subido, cfg intacto.
+    with open(os.path.join(lib, "demo_skill", "recipe.json"), encoding="utf-8") as f:
+        cur = json.load(f)
+    assert cur["params"]["steps"] == 32
+    assert cur["params"]["cfg"] == 6.0
+    assert cur["version"] == "1.1.0"
+
+    # growth_log: una línea con la evidencia.
+    with open(os.path.join(lib, "demo_skill", "growth_log.jsonl"), encoding="utf-8") as f:
+        lines = [json.loads(x) for x in f if x.strip()]
+    assert len(lines) == 1
+    entry = lines[0]
+    assert entry["version"] == "1.1.0"
+    assert entry["score_before"] == 6.5
+    assert entry["score_after"] == 7.4
+    assert entry["judge_run_id"] == "judge_xyz"
+    assert entry["diff"] == {"params": {"steps": 32}}
+
+
+def test_edge_major_y_patch(tmp_path):
+    lib = str(tmp_path)
+    _seed_skill(lib, slug="s_major", version="1.4.2")
+    r1 = comfyui_bump_skill_version("s_major", "rework", score_before=5.0, score_after=8.0,
+                                    bump="major", library_dir=lib)
+    assert r1["new_version"] == "2.0.0"
+
+    _seed_skill(lib, slug="s_patch", version="1.4.2")
+    r2 = comfyui_bump_skill_version("s_patch", "tweak", score_before=5.0, score_after=5.1,
+                                    bump="patch", library_dir=lib)
+    assert r2["new_version"] == "1.4.3"
+
+
+def test_error_gate_bloquea_si_no_mejora(tmp_path):
+    lib = str(tmp_path)
+    sdir = _seed_skill(lib)
+    res = comfyui_bump_skill_version("demo_skill", "no mejora", score_before=7.0,
+                                     score_after=6.5, library_dir=lib)
+    assert res["ok"] is False
+    assert "gate" in res["error"]
+    # No se tocó nada: ni snapshot ni growth_log ni cambio de versión.
+    assert not os.path.exists(os.path.join(sdir, "growth_log.jsonl"))
+    with open(os.path.join(sdir, "recipe.json"), encoding="utf-8") as f:
+        assert json.load(f)["version"] == "1.0.0"
+
+
+def test_error_force_salta_gate(tmp_path):
+    lib = str(tmp_path)
+    _seed_skill(lib)
+    res = comfyui_bump_skill_version("demo_skill", "forzado", score_before=7.0,
+                                     score_after=6.5, force=True, library_dir=lib)
+    assert res["ok"] is True
+    assert res["new_version"] == "1.1.0"
+    assert res["growth_entry"]["forced"] is True
+
+
+def test_error_skill_inexistente(tmp_path):
+    res = comfyui_bump_skill_version("no_existe", "x", score_before=1.0, score_after=2.0,
+                                     library_dir=str(tmp_path))
+    assert res["ok"] is False
+    assert "no encontrada" in res["error"]
+
+
+if __name__ == "__main__":
+    sys.exit(pytest.main([__file__, "-q"]))

python/functions/ml/tests/test_comfyui_update_skill_score.py

@@ -0,0 +1,75 @@
+"""Tests offline para comfyui_update_skill_score (impura, sin red).
+
+- golden: media incremental correcta tras varios juicios; reescribe in-place sin crear
+  snapshots ni growth_log,
+- edge: arranca desde score_mean/score_n ausentes (skill recién creada),
+- error: skill inexistente / score no numérico → ok=False.
+"""
+
+import json
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(__file__))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
+
+import pytest  # noqa: E402
+
+from ml.comfyui_update_skill_score import comfyui_update_skill_score  # noqa: E402
+
+
+def _seed(lib, slug="demo", **extra):
+    sdir = os.path.join(lib, slug)
+    os.makedirs(sdir, exist_ok=True)
+    recipe = {"schema_version": 1, "slug": slug, "version": "1.0.0",
+              "base_workflow": "txt2img", **extra}
+    with open(os.path.join(sdir, "recipe.json"), "w", encoding="utf-8") as f:
+        json.dump(recipe, f)
+    return sdir
+
+
+def test_golden_media_incremental(tmp_path):
+    lib = str(tmp_path)
+    sdir = _seed(lib, score_mean=0.0, score_n=0)
+
+    r1 = comfyui_update_skill_score("demo", 7.0, library_dir=lib)
+    assert r1["ok"] and r1["score_n"] == 1 and r1["score_mean"] == 7.0
+
+    r2 = comfyui_update_skill_score("demo", 8.0, library_dir=lib)
+    assert r2["score_n"] == 2 and r2["score_mean"] == 7.5
+
+    r3 = comfyui_update_skill_score("demo", 6.0, library_dir=lib)
+    assert r3["score_n"] == 3
+    assert abs(r3["score_mean"] - 7.0) < 1e-9  # (7+8+6)/3
+
+    # in-place: ni versions/ ni growth_log creados por este helper.
+    assert not os.path.exists(os.path.join(sdir, "versions"))
+    assert not os.path.exists(os.path.join(sdir, "growth_log.jsonl"))
+
+    with open(os.path.join(sdir, "recipe.json"), encoding="utf-8") as f:
+        cur = json.load(f)
+    assert cur["score_n"] == 3
+
+
+def test_edge_sin_campos_previos(tmp_path):
+    lib = str(tmp_path)
+    _seed(lib, slug="fresh")  # sin score_mean/score_n
+    res = comfyui_update_skill_score("fresh", 9.0, library_dir=lib)
+    assert res["ok"] and res["score_mean"] == 9.0 and res["score_n"] == 1
+    assert res["prev_score_n"] == 0
+
+
+def test_error_skill_inexistente(tmp_path):
+    res = comfyui_update_skill_score("nope", 5.0, library_dir=str(tmp_path))
+    assert res["ok"] is False and "no encontrada" in res["error"]
+
+
+def test_error_score_no_numerico(tmp_path):
+    lib = str(tmp_path)
+    _seed(lib, slug="x", score_mean=0.0, score_n=0)
+    res = comfyui_update_skill_score("x", "siete", library_dir=lib)
+    assert res["ok"] is False and "numérico" in res["error"]
+
+
+if __name__ == "__main__":
+    sys.exit(pytest.main([__file__, "-q"]))