Fix: ship datasets.json in the wheel (0.2.1)

labagent/__init__.py

@@ -1,3 +1,3 @@
 """labagent: launch and tear down hands-on labs (RAG, LLM, Databricks) and AWS training sandboxes."""
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"

pyproject.toml

@@ -59,6 +59,7 @@ labagent = [
   "terraform/*/.terraform.lock.hcl",
   "terraform/*/tests/*.tftest.hcl",
   "packs/*/sources/*.jsonl",
+  "packs/*/sources/*.json",
   "packs/*/app/*",
   "packs/*/app/static/*",
 ]

tests/test_packaging.py

@@ -0,0 +1,31 @@
+"""Every data file the code reads at runtime must be shipped in the wheel. Source-tree tests cannot see this: a missing
+package-data pattern only breaks users who install from PyPI (this happened in 0.2.0: datasets.json was left out)."""
+import fnmatch
+import re
+from pathlib import Path
+
+ROOT = Path(__file__).parent.parent
+PKG = ROOT / "labagent"
+SKIP_PARTS = {"__pycache__", ".terraform"}
+
+
+def patterns():
+    text = (ROOT / "pyproject.toml").read_text()
+    block = re.search(r"\[tool\.setuptools\.package-data\]\s*labagent = \[(.*?)\]", text, re.S).group(1)
+    return re.findall(r'"([^"]+)"', block)
+
+
+def test_every_runtime_data_file_is_covered_by_package_data():
+    pats = patterns()
+    missing = []
+    for f in PKG.rglob("*"):
+        if not f.is_file() or f.suffix in (".py", ".pyc") or SKIP_PARTS & set(f.parts) or f.name == "ui.json":
+            continue
+        rel = f.relative_to(PKG).as_posix()
+        if not any(fnmatch.fnmatch(rel, p) for p in pats):
+            missing.append(rel)
+    assert not missing, f"not shipped in the wheel: {missing}"
+
+
+def test_the_dataset_registry_pin_is_shipped():
+    assert any(fnmatch.fnmatch("packs/rag/sources/datasets.json", p) for p in patterns())