Fix index-contract API, add fake tests for parsing/invoice templates (#270)

- extract-reconcile-invoice: index_contract.py called files.get_file /
  files.read_file_content / files.upload_file (v1 SDK surface removed in
  v2), breaking every Upload Contract click. Switched to files.list +
  files.get + files.create.
- Added test_index_contract_workflow and test_metadata_workflow to
  exercise the full v2 surface (files.list, files.get, pipelines.upsert,
  pipelines.documents.upsert, configurations.retrieve).
- document-parsing and invoice-extraction had only placeholder tests —
  wired up llama-cloud-fake and added parametrized tests covering every
  tier/mode. invoice-extraction's test drives the HIL step.
- Bumped requires-python to >=3.12 on both (fake floor).

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "hatchling.build"
 name = "invoice-extraction"
 version = "0.1.0"
 description = "A workflow that, given an invoice, extracts several key details using LlamaExtract"
-requires-python = ">=3.10"
+requires-python = ">=3.12"
 readme = "README.md"
 dependencies = [
   "llama-index-workflows>=2.16.0,<3.0.0",
@@ -18,10 +18,17 @@ dev = [
     "hatch>=1.14.2",
     "pytest>=8.4.2",
     "pytest-asyncio>=1.3.0",
+    "pytest-timeout>=2.3.1",
+    "llama-cloud-fake>=0.1,<0.2",
     "ruff>=0.13.2",
     "ty>=0.0.2",
 ]
 
+[tool.pytest.ini_options]
+timeout = 120
+timeout_method = "thread"
+asyncio_mode = "auto"
+
 [tool.hatch.envs.default.scripts]
 format = "ruff format ."
 format-check = "ruff format --check ."

tests/conftest.py

@@ -0,0 +1,20 @@
+"""Pytest configuration: install the LlamaCloud fake server for all tests."""
+
+import logging
+import sys
+
+import pytest
+from llama_cloud_fake import FakeLlamaCloudServer
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    handlers=[logging.StreamHandler(sys.stdout)],
+)
+
+_fake = FakeLlamaCloudServer().install()
+
+
+@pytest.fixture
+def fake() -> FakeLlamaCloudServer:
+    return _fake

tests/test_placeholder.py

@@ -1,12 +0,0 @@
-"""Placeholder test file.
-
-Replace this with actual tests for your project.
-"""
-
-
-def test_placeholder() -> None:
-    """Placeholder test that always passes.
-
-    Remove this test once you add real tests to your project.
-    """
-    assert True

tests/test_workflow.py

@@ -0,0 +1,32 @@
+import pytest
+from invoice_extraction.workflow import (
+    FeedbackRequiredEvent,
+    HumanFeedbackEvent,
+    workflow,
+)
+from llama_cloud_fake import FakeLlamaCloudServer
+
+
+@pytest.mark.parametrize("extraction_mode", ["base", "advanced", "premium"])
+async def test_invoice_extraction_workflow(
+    monkeypatch: pytest.MonkeyPatch,
+    fake: FakeLlamaCloudServer,
+    extraction_mode: str,
+) -> None:
+    """Exercise files.create + extract.create + wait_for_completion via the fake,
+    then approve through the human-in-the-loop step."""
+    monkeypatch.setenv("LLAMA_CLOUD_API_KEY", "fake-api-key")
+    handler = workflow.run(
+        path="tests/files/test.pdf",
+        extraction_mode=extraction_mode,
+    )
+    feedback_event: FeedbackRequiredEvent | None = None
+    async for ev in handler.stream_events():
+        if isinstance(ev, FeedbackRequiredEvent):
+            feedback_event = ev
+            handler.ctx.send_event(HumanFeedbackEvent(approved=True))
+            break
+    result = await handler
+    assert feedback_event is not None
+    assert isinstance(feedback_event.extraction_result, str)
+    assert result == feedback_event.extraction_result