apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-07-15 21:11:05 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix: prompt guidance referenced fields get_document doesn't return

Browse source 
OPEN_SYSTEM_PROMPT and SCOPED_SYSTEM_PROMPT told the agent to call
get_document(doc_id) "to confirm status and page/line count", but neither
backend returns a page/line count and the local backend has no status field
(get_document returns doc_name/doc_type/doc_description). The agent would
hunt for fields that don't exist, degrading QA. Align both prompts with the
demo's wording ("confirm the document's name and type"). Regression test
asserts the prompts no longer reference the non-existent page/line count.
This commit is contained in:
mountain 2026-07-10 10:53:43 +08:00
parent 9ad7c687e0
commit e18ccdeaf8
2 changed files with 12 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/test_agent.py
View file

@ -20,6 +20,16 @@ def test_scoped_prompt_omits_list_documents():
assert "get_page_content" in SCOPED_SYSTEM_PROMPT
def test_prompts_get_document_guidance_matches_returned_fields():
# Regression: get_document returns doc_name/doc_type/doc_description — neither
# backend returns a page/line count, and the local backend has no status
# field. The prompt must not send the agent hunting for fields that don't
# exist (degrades QA), so it references only name and type (like the demo).
for prompt in (OPEN_SYSTEM_PROMPT, SCOPED_SYSTEM_PROMPT):
assert "page/line count" not in prompt
assert "get_document(doc_id) to confirm the document's name and type" in prompt
def test_wrap_with_doc_context_cannot_be_escaped_by_untrusted_content():
"""doc_name/doc_description are untrusted (doc_name is an unsanitized
filename; doc_description is LLM-generated from document content). Neither