Author runnable skill bodies via OpenAI-compatible codegen model

create_skill now writes a real predict/act body: the small decision model
still authors title + description (engine.generate), then a larger
OpenAI-compatible model (default qwen38-iq3s) writes the runnable code
against the SKILL.md contract. Bodies persist to data/skills/<cat>/<name>.py,
are hot-loaded via importlib, merged into the running tree, and the request
re-dispatches to the new leaf. The dashboard decision-flow view shows the
title/description with a writing badge while the body is being written.
Codegen failure degrades to a navigable stub.

tests/integration/test_pipeline.py

@@ -12,10 +12,20 @@ from pathlib import Path
 import pytest
 
 from semif_agent.cli import build_scheduler, load_config
+from semif_agent.codegen import CodegenClient, generate_skill_body
 from semif_agent.decisions import Request
 from semif_agent.dream import dream
 from semif_agent.engine import EngineUnavailable
-from semif_agent.skills import CategoryDraft, SkillDraft, generate_category, generate_skill
+from semif_agent.skills import (
+    CategoryDraft,
+    SkillBodyStore,
+    SkillDraft,
+    build_skills,
+    build_tree,
+    generate_category,
+    generate_skill,
+    materialize_skill,
+)
 
 
 def require_real(config: dict):
@@ -140,6 +150,38 @@ def test_generate_skill(tmp_path):
     assert draft.name and draft.description
 
 
+def test_generate_skill_body_codegen(tmp_path):
+    """A real OpenAI-compatible model writes a runnable skill body.
+
+    Slow: uses the big codegen model (qwen38-iq3s by default). Run this one in
+    the background and poll — long-lived ssh sessions get SIGHUP'd.
+    """
+    config = load_config()
+    require_real(config)
+    codegen_cfg = config.get("codegen", {})
+    client = CodegenClient(
+        base_url=codegen_cfg.get("base_url", "http://localhost:11434/v1"),
+        model=codegen_cfg.get("model", "qwen38-iq3s"),
+        timeout=float(codegen_cfg.get("timeout", 600.0)),
+    )
+    tree = build_tree(build_skills({"skills": {}}))
+    draft = SkillDraft(
+        name="check_service",
+        description="Check whether a service is reachable.",
+    )
+    code = generate_skill_body(
+        client,
+        Request("is my home server reachable right now?"),
+        "tracking",
+        draft,
+        tree,
+    )
+    print(f"generated {len(code)} bytes of skill body")
+    store = SkillBodyStore(str(tmp_path / "skills"))
+    skill = materialize_skill(draft, "tracking", store)
+    assert callable(skill.predict) and callable(skill.act)
+
+
 def test_create_skill_empty_category_does_not_wedge(tmp_path):
     """A dispatch that lands on an empty category must not leave the scheduler wedged.