Files
Conflict_Checker/tests/agents/test_extraction_ladder.py
T
woogi fe09e4a66b
Docker Release / build-and-push (push) Successful in 1m14s
Docker Release / release (push) Skipped
feat: coverage-driven extraction retry ladder (agent path)
2026-08-18 13:38:30 -05:00

87 lines
4.4 KiB
Python

from backend import config
from backend.agents.base import AgentScope, AgentUsage
from backend.agents.extractors import SheetExtractorAgent
from backend.prompts import TEXT_STRUCTURING_SYSTEM_PROMPT, TEXT_STRUCTURING_USER_INSTRUCTION
def test_text_structuring_prompt_demands_verbatim_and_completeness():
assert "verbatim" in TEXT_STRUCTURING_USER_INSTRUCTION.lower()
assert "every" in TEXT_STRUCTURING_USER_INSTRUCTION.lower()
assert "{text_layer}" in TEXT_STRUCTURING_USER_INSTRUCTION
def _page(n=8, text="1. \nALL SAWN LUMBER IN CONTACT WITH SOIL TO BE SOUTHERN PINE, PRESSURE TREATED.\n2. \nROOF SHEATHING: 5/8\" PLYWOOD, C-D GRADE, STRUCTURAL I."):
return {"page_number": n, "base64": "AAAA", "text_layer": text}
def _run(agent, page, hint=""):
scope = AgentScope(scope_id=f"sheet:{page['page_number']}",
payload={"page": page, "sheet_hint": hint})
result = agent.run(scope)
assert not result.error, result.error
return result.artifacts[0]
def test_ladder_falls_back_when_vision_returns_nothing(monkeypatch):
# vision pass returns 1 summary object that the guard drops;
# text-structuring disabled to exercise the deterministic rung
monkeypatch.setattr("backend.agents.extractors.call_json",
lambda **kw: [{"name": "general notes", "value": "notes"}])
monkeypatch.setattr("backend.config.EXTRACT_TEXT_RETRY_ENABLED", False)
agent = SheetExtractorAgent(AgentUsage())
sheet = _run(agent, _page())
assert sheet["assertions"], "dark sheet must be impossible with fallback enabled"
assert all(a.get("grounding") == "text_layer_fallback" for a in sheet["assertions"])
assert sheet["coverage"]["ratio"] >= 0.6
def test_ladder_merge_preserves_graphical_objects(monkeypatch):
# vision finds a graphical symbol; text rung adds notes.
# The graphical object MUST survive the merge.
calls = {"n": 0}
def fake_call_json(**kw):
calls["n"] += 1
if kw.get("images_b64"): # vision pass
return {"sheet": {}, "objects": [
{"object_id": "g1", "object_type": "lighting_fixture",
"name": "pendant at grid C-4", "source_text": None,
"graphical_basis": "16in pendant symbol at grid C-4"}]}
return {"sheet": {}, "objects": [ # text-structuring pass
{"object_id": "t1", "object_type": "general_note",
"source_text": "ALL SAWN LUMBER IN CONTACT WITH SOIL TO BE SOUTHERN PINE, PRESSURE TREATED.",
"name": "lumber note"}]}
monkeypatch.setattr("backend.agents.extractors.call_json", fake_call_json)
agent = SheetExtractorAgent(AgentUsage())
sheet = _run(agent, _page())
assert calls["n"] >= 2, "text-structuring rung should have fired"
assert any(a.get("graphical_basis") for a in sheet["assertions"])
assert any("SAWN LUMBER" in (a.get("source_text") or "") for a in sheet["assertions"])
def test_ladder_recovers_sheet_number_from_text_layer(monkeypatch):
monkeypatch.setattr(
"backend.agents.extractors.call_json",
lambda **kw: {"sheet": {}, "objects": [
{"object_id": "o1", "name": "RCP note",
"source_text": "GYP. BD. CEILING 8'-11 3/8\" A.F.F. TYP. FOR ALL STOREFRONT",
"attributes": {"height": "8'-11 3/8\""}}]})
agent = SheetExtractorAgent(AgentUsage())
sheet = _run(agent, _page(18, "REFLECTED CEILING PLAN\nGYP. BD. CEILING 8'-11 3/8\" A.F.F. TYP. FOR ALL STOREFRONT\nA102"))
assert sheet["sheet_number"] == "A102"
def test_ladder_skips_retry_when_coverage_healthy(monkeypatch):
# vision covers every meaningful text-layer line -> no rung 2/3 calls
calls = {"n": 0}
def fake_call_json(**kw):
calls["n"] += 1
return {"sheet": {"sheet_number": "A101"}, "objects": [
{"object_id": "o1", "object_type": "general_note", "name": "lumber note",
"source_text": "ALL SAWN LUMBER IN CONTACT WITH SOIL TO BE SOUTHERN PINE, PRESSURE TREATED."},
{"object_id": "o2", "object_type": "general_note", "name": "sheathing note",
"source_text": "ROOF SHEATHING: 5/8\" PLYWOOD, C-D GRADE, STRUCTURAL I."}]}
monkeypatch.setattr("backend.agents.extractors.call_json", fake_call_json)
agent = SheetExtractorAgent(AgentUsage())
sheet = _run(agent, _page())
assert sheet["coverage"]["ratio"] >= config.EXTRACT_COVERAGE_FLOOR
assert calls["n"] == 1