apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-15 20:05:14 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix(filesystem): relax structural read limits

Browse source
This commit is contained in:
BukeLy 2026-05-26 20:57:08 +08:00
parent 2b69719f60
commit cd571ddbaf
4 changed files with 52 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

44
tests/test_pageindex_structural_read.py
View file

@ -474,22 +474,48 @@ def test_cat_structure_page_node_and_text_outputs_are_hard_limited():
assert len(second_structure["data"]["structure"]) == 5
assert second_structure["data"]["structure"][0]["node_id"] == "0026"
pages = json.loads(executor.execute("cat dsid_limited_pdf --page 1-3"))
assert pages["data"]["text"] == "Page 1 text\n\nPage 2 text\n\nPage 3 text"
assert pages["data"]["page_pagination"]["limit"] == 3
with pytest.raises(PIFSCommandError, match="at most 3"):
executor.execute("cat dsid_limited_pdf --page 1-4")
pages = json.loads(executor.execute("cat dsid_limited_pdf --page 1-5"))
assert pages["data"]["text"] == (
"Page 1 text\n\nPage 2 text\n\nPage 3 text\n\nPage 4 text\n\nPage 5 text"
)
assert pages["data"]["page_pagination"]["limit"] == 5
with pytest.raises(PIFSCommandError, match="at most 5"):
executor.execute("cat dsid_limited_pdf --page 1-6")
with pytest.raises(PIFSCommandError, match="evidence is sufficient"):
executor.execute("cat dsid_limited_pdf --page 1-6")
nodes = json.loads(
executor.execute("cat dsid_limited_pdf --node 0001 0002 0003 0004 0005")
executor.execute(
"cat dsid_limited_pdf --node 0001 0002 0003 0004 0005 "
"0006 0007 0008 0009 0010"
)
)
assert nodes["data"]["node_ids"] == ["0001", "0002", "0003", "0004", "0005"]
assert nodes["data"]["node_ids"] == [
"0001",
"0002",
"0003",
"0004",
"0005",
"0006",
"0007",
"0008",
"0009",
"0010",
]
comma_nodes = json.loads(
executor.execute("cat dsid_limited_pdf --node 0001,0002")
)
assert comma_nodes["data"]["node_ids"] == ["0001", "0002"]
with pytest.raises(PIFSCommandError, match="at most 5"):
executor.execute("cat dsid_limited_pdf --node 0001 0002 0003 0004 0005 0006")
with pytest.raises(PIFSCommandError, match="at most 10"):
executor.execute(
"cat dsid_limited_pdf --node 0001 0002 0003 0004 0005 "
"0006 0007 0008 0009 0010 0011"
)
with pytest.raises(PIFSCommandError, match="continue with additional chunks"):
executor.execute(
"cat dsid_limited_pdf --node 0001 0002 0003 0004 0005 "
"0006 0007 0008 0009 0010 0011"
)
with pytest.raises(PIFSCommandError, match="cat accepts one file target"):
executor.execute("cat dsid_limited_pdf 0001")

2
tests/test_pifs_agent_stream.py
View file

@ -202,6 +202,8 @@ class PIFSAgentStreamTest(unittest.TestCase):
self.assertIn("prefer cat <target> --node <node_id>", AGENT_TOOL_POLICY)
self.assertIn("page-level evidence", AGENT_TOOL_POLICY)
self.assertIn("prefer\ncat <path> --node <node_id>", BASH_TOOL_DESCRIPTION)
self.assertIn("stop if the evidence is sufficient", AGENT_TOOL_POLICY)
self.assertIn("continue with another chunk before answering", BASH_TOOL_DESCRIPTION)
def test_prompt_requires_stat_for_metadata_questions(self):
self.assertIn("stat --schema and stat <target>", AGENT_TOOL_POLICY)