bikoret/vav_pipeline/test/urim_v_tumim_test.exs

defmodule VavPipeline.UrimVTumimTest do
  @moduledoc """
  Tests for L2 — Urim v'Tumim (Architecture §2, PRD §4.7).

  The Urim v'Tumim is the decision oracle interface, consulted only on
  high-stakes teiku cases the Sanhedrin cannot resolve. It NEVER fabricates
  certainty — it returns one of three honest outcomes:

    1. resolved_by_specification — re-read produced an answer
    2. resolved_by_external — external testimony recorded (not binding)
    3. deferred_to_human — the system stops, human judgment required

  Bamidbar 27:21 — al-piv yetz'u v'al-piv yavo'u.
  By the Urim's word the people go out and come in. Not the system's word.
  """

  use ExUnit.Case, async: false

  alias VavPipeline.UrimVTumim

  setup do
    # Reset state by replacing hooks with defaults each test.
    GenServer.call(UrimVTumim, {:set_hook, :specification_consult, &UrimVTumim.default_specification_consult/1})
    GenServer.call(UrimVTumim, {:set_hook, :external_consult, &UrimVTumim.default_external_consult/1})
    :ok
  end

  defp valid_input(overrides \\ %{}) do
    Map.merge(
      %{
        case_id: "case_#{:rand.uniform(1_000_000)}",
        question: "When two principles conflict, which takes precedence?",
        context: %{torah_refs: ["Shemot 35:3", "Vayikra 18:5"]},
        stakes: :high,
        sanhedrin_teiku: true
      },
      overrides
    )
  end

  # ============================================================
  # Pre-condition gating
  # ============================================================

  describe "pre-condition gating" do
    test "refuses cases that did not reach Sanhedrin teiku first" do
      # Urim is consulted AFTER teiku, never instead of Sanhedrin.
      input = valid_input(%{sanhedrin_teiku: false})
      assert {:error, :not_eligible} = UrimVTumim.consult(input)
    end

    test "refuses ordinary-stakes cases" do
      # Only national-importance cases escalate to the Urim.
      input = valid_input(%{stakes: :ordinary})
      assert {:error, :not_eligible} = UrimVTumim.consult(input)
    end

    test "refuses missing case_id" do
      input = valid_input() |> Map.delete(:case_id)
      assert {:error, _} = UrimVTumim.consult(input)
    end

    test "refuses empty question" do
      input = valid_input(%{question: ""})
      assert {:error, :invalid_input} = UrimVTumim.consult(input)
    end
  end

  # ============================================================
  # Outcome 1: resolved by specification
  # ============================================================

  describe "specification re-read" do
    test "specification consult resolves the case" do
      GenServer.call(UrimVTumim, {:set_hook, :specification_consult,
        fn _input ->
          {:resolved, %{verses: ["Shemot 35:3"], reading: "Shabbat is absolute"}}
        end
      })

      input = valid_input()
      assert {:ok, {:resolved_by_specification, evidence}} = UrimVTumim.consult(input)
      assert evidence.reading == "Shabbat is absolute"
    end

    test "specification resolution is recorded with steps_taken=[:specification]" do
      GenServer.call(UrimVTumim, {:set_hook, :specification_consult,
        fn _input -> {:resolved, %{ok: true}} end
      })

      input = valid_input()
      {:ok, _} = UrimVTumim.consult(input)
      {:ok, record} = UrimVTumim.get_record(input.case_id)
      assert record.steps_taken == [:specification]
    end
  end

  # ============================================================
  # Outcome 2: resolved by external (testimony, not ruling)
  # ============================================================

  describe "external consultation" do
    setup do
      GenServer.call(UrimVTumim, {:set_hook, :external_consult,
        fn _input ->
          {:ok, %{
            provenance: :claude,
            reading: "Pikuach nefesh overrides — testimony only",
            propositions: ["overrides(pikuach_nefesh, shabbat_lo_taaseh)"]
          }}
        end
      })
      :ok
    end

    test "external consultation succeeds when specification fails" do
      input = valid_input()
      assert {:ok, {:resolved_by_external, consultation}} = UrimVTumim.consult(input)
      assert consultation.provenance == :claude
    end

    test "steps_taken records both specification attempt and external consult" do
      input = valid_input()
      {:ok, _} = UrimVTumim.consult(input)
      {:ok, record} = UrimVTumim.get_record(input.case_id)
      assert record.steps_taken == [:specification, :external]
    end
  end

  # ============================================================
  # Outcome 3: deferred to human (the honest refusal)
  # ============================================================

  describe "deferral to human" do
    test "defers when both specification and external fail" do
      # Both hooks return their default failure modes.
      input = valid_input()
      assert {:ok, {:deferred_to_human, reason}} = UrimVTumim.consult(input)
      assert is_binary(reason)
      assert reason =~ "Human judgment required"
    end

    test "deferred record has steps_taken with :deferred at the end" do
      input = valid_input()
      {:ok, _} = UrimVTumim.consult(input)
      {:ok, record} = UrimVTumim.get_record(input.case_id)
      assert record.steps_taken == [:specification, :external, :deferred]
    end

    test "the Urim refuses to fabricate certainty (PRD 4.7)" do
      # When both consultations fail, the Urim does NOT return any
      # invented answer — it deliberately stops and asks for human judgment.
      input = valid_input()
      {:ok, outcome} = UrimVTumim.consult(input)
      assert match?({:deferred_to_human, _}, outcome)
    end
  end

  # ============================================================
  # Records & stats
  # ============================================================

  describe "records and stats" do
    test "consultations are recorded in chronological order" do
      before_count = length(UrimVTumim.records())

      input1 = valid_input(%{case_id: "rec_test_1"})
      input2 = valid_input(%{case_id: "rec_test_2"})

      {:ok, _} = UrimVTumim.consult(input1)
      {:ok, _} = UrimVTumim.consult(input2)

      records = UrimVTumim.records()
      assert length(records) >= before_count + 2
      ids = Enum.map(records, & &1.case_id)
      assert "rec_test_1" in ids
      assert "rec_test_2" in ids
    end

    test "stats track outcomes" do
      stats = UrimVTumim.stats()
      assert is_integer(stats.total)
      assert is_integer(stats.resolved_by_specification)
      assert is_integer(stats.resolved_by_external)
      assert is_integer(stats.deferred_to_human)
      assert stats.total ==
               stats.resolved_by_specification + stats.resolved_by_external +
                 stats.deferred_to_human
    end

    test "get_record returns :not_found for unknown case_id" do
      assert :not_found = UrimVTumim.get_record("nonexistent_xyz")
    end
  end
end