Agent-Course-Submission / tests /test_graph.py
DriptoBhattacharyya's picture
Slim graph + cap tool rounds for gateway latency; pin gpt-oss-120b
6fe947e
Raw
History Blame Contribute Delete
2.06 kB
"""Tests for graph wiring, routing, and the judge evaluation loop."""
from types import SimpleNamespace
from unittest.mock import MagicMock, patch
from gaia_agent.nodes import (
judge,
route_after_judge,
route_after_research,
)
from gaia_agent.schemas import JudgeVerdict
def test_graph_compiles():
from gaia_agent.graph import graph
assert graph.name == "GAIA Agent"
nodes = set(graph.get_graph().nodes.keys())
assert {"ingest_file", "research", "tools", "solver", "judge", "formatter"} <= nodes
def test_route_after_research_tools_vs_solver():
with_calls = SimpleNamespace(tool_calls=[{"name": "tavily_search"}])
without = SimpleNamespace(tool_calls=[])
assert route_after_research({"messages": [with_calls]}) == "tools"
assert route_after_research({"messages": [without]}) == "solver"
def test_route_after_judge_pass():
state = {"verdict": JudgeVerdict(verdict="PASS"), "attempts": 0}
assert route_after_judge(state) == "formatter"
def test_route_after_judge_revise_within_budget():
state = {"verdict": JudgeVerdict(verdict="REVISE"), "attempts": 0}
with patch("gaia_agent.nodes.get_settings", return_value=SimpleNamespace(max_judge_retries=1)):
assert route_after_judge(state) == "research"
def test_route_after_judge_revise_budget_exhausted():
state = {"verdict": JudgeVerdict(verdict="REVISE"), "attempts": 1}
with patch("gaia_agent.nodes.get_settings", return_value=SimpleNamespace(max_judge_retries=1)):
assert route_after_judge(state) == "formatter"
def test_judge_increments_attempts_on_revise():
structured = MagicMock()
structured.invoke.return_value = JudgeVerdict(
verdict="REVISE", feedback="wrong format", missing=["units"]
)
with patch("gaia_agent.nodes.get_structured_llm", return_value=structured):
out = judge({"question": "q", "candidate": None, "attempts": 0})
assert out["attempts"] == 1
assert out["verdict"].verdict == "REVISE"
assert "messages" in out # feedback injected back into the loop