Phase 1-2 build: Steps 5-6, 8-13

Shoresh Engine (Haskell, Step 5)
- 12 modules: Types, Lexicon, Binyanim, Teamim, Gematria, Graph,
  KetivQere, Smikhut, Havdalah, Kriah, KiTov, Firmware
- 33 EUnit tests, 0 failures
- Firmware module verifies L1 SHA-256 hash at startup

Talmudic Engine (SWI-Prolog, Step 6)
- 15 modules: halt, reasoning, specification, interface
- 57 PlUnit tests, 0 failures
- Three cardinal halt conditions: avodah_zarah, shfichut_damim, gilui_arayot

Vav Pipeline (Elixir, Steps 8-11)
- 14 modules: BereishitCycle, Shema, Cloud, Manna, L1Reader,
  Specification, HaltConditions, ShabbatTimer, CycleLog, Chatzotzrot,
  ShoreshEngineClient, TalmudicEngineClient, Application
- 46 ExUnit tests, 0 failures
- Nishma-first architecture: hears before it speaks

Sanhedrin Framework (Erlang/OTP, Step 12)
- 8 modules: sanhedrin_app, sanhedrin_sup, escalation, panel_sup,
  panel, judge, clerk, halt_monitor
- 46 EUnit tests, 0 failures (includes fix: rejected outcome now reachable)
- Panel sizes: 1/3/23/71 — unanimous capital guilty → acquit (Sanhedrin 17a)
- Minority opinions append-only, never deleted

Korban Processor (Python, Step 13)
- 6 modules: korban, shechitah, semichah, zerikah, haktarah, router

Builder tooling: AGENTS.md, opencode.json, memory/, src/tools/

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

talmudic_engine/src/reasoning/interpret.pl

@@ -0,0 +1,114 @@
+%% interpret.pl — Interpretation generation.
+%%
+%% Architecture §3.4:
+%%   interpret(Case, Interpretation) :-
+%%       find_relevant_mitzvot(Case, Mitzvot),
+%%       find_relevant_verses(Case, Verses),
+%%       construct_interpretation(Mitzvot, Verses, Interpretation).
+%%
+%% An interpretation is grounded in Torah — it consists of:
+%%   1. Relevant mitzvot that apply to the case
+%%   2. Relevant verses that inform the case
+%%   3. A constructed reading that connects them
+
+:- module(interpret, [
+    interpret/2,
+    find_relevant_mitzvot/2,
+    find_relevant_verses/2,
+    construct_interpretation/4
+]).
+
+:- use_module('../specification/mitzvot').
+:- use_module('../specification/torah_text').
+:- use_module('../specification/root_meanings').
+:- use_module('../specification/relationships').
+
+%% A case is represented as:
+%%   case(Ref, Domain, Roots, Question)
+%%   - Ref: a unique identifier
+%%   - Domain: the semantic domain of the question
+%%   - Roots: list of Hebrew roots involved
+%%   - Question: the question being asked
+
+%% ============================================================
+%% INTERPRETATION
+%% ============================================================
+
+%% Propose an interpretation of a case.
+%% An interpretation is:
+%%   interpretation(CaseRef, Mitzvot, Verses, Reading, Confidence)
+interpret(Case, Interpretation) :-
+    Case = case(Ref, _Domain, _Roots, _Question),
+    find_relevant_mitzvot(Case, Mitzvot),
+    find_relevant_verses(Case, Verses),
+    construct_interpretation(Ref, Mitzvot, Verses, Interpretation).
+
+%% ============================================================
+%% FIND RELEVANT MITZVOT
+%% ============================================================
+
+%% Strategy: find mitzvot in the same domain as the case,
+%% plus mitzvot whose source verses share roots with the case.
+find_relevant_mitzvot(case(_Ref, Domain, Roots, _Question), Mitzvot) :-
+    %% Mitzvot in the same domain
+    findall(mitzvah(ID, Cat, Action, Cond),
+            (   mitzvah_domain(ID, Domain),
+                mitzvah(ID, Cat, Action, Cond)
+            ),
+            DomainMitzvot),
+    %% Mitzvot whose source verses share roots with the case
+    findall(mitzvah(ID, Cat, Action, Cond),
+            (   mitzvah_source(ID, ref(Book, Ch, Vs)),
+                verse(Book, Ch, Vs, VerseRoots, _),
+                member(Root, Roots),
+                member(Root, VerseRoots),
+                mitzvah(ID, Cat, Action, Cond)
+            ),
+            RootMitzvot),
+    append(DomainMitzvot, RootMitzvot, AllMitzvot),
+    sort(AllMitzvot, Mitzvot).  % remove duplicates
+
+%% ============================================================
+%% FIND RELEVANT VERSES
+%% ============================================================
+
+%% Strategy: find verses that mention any of the case's roots.
+find_relevant_verses(case(_Ref, _Domain, Roots, _Question), Verses) :-
+    findall(verse_ref(Book, Ch, Vs, Gloss),
+            (   member(Root, Roots),
+                verse(Book, Ch, Vs, VerseRoots, Gloss),
+                member(Root, VerseRoots)
+            ),
+            AllVerses),
+    sort(AllVerses, Verses).  % remove duplicates
+
+%% ============================================================
+%% CONSTRUCT INTERPRETATION
+%% ============================================================
+
+%% Build an interpretation from the collected mitzvot and verses.
+%% Confidence is based on the strength of grounding:
+%%   - high: both mitzvot and verses found
+%%   - medium: only mitzvot or only verses
+%%   - low: neither (but still generates a minimal reading)
+construct_interpretation(CaseRef, Mitzvot, Verses, Interpretation) :-
+    assess_confidence(Mitzvot, Verses, Confidence),
+    build_reading(Mitzvot, Verses, Reading),
+    Interpretation = interpretation(CaseRef, Mitzvot, Verses, Reading, Confidence).
+
+%% Assess confidence based on grounding
+assess_confidence(Mitzvot, Verses, high) :-
+    Mitzvot \= [],
+    Verses \= [], !.
+assess_confidence(Mitzvot, _, medium) :-
+    Mitzvot \= [], !.
+assess_confidence(_, Verses, medium) :-
+    Verses \= [], !.
+assess_confidence(_, _, low).
+
+%% Build a reading — the interpretive connection between sources
+build_reading(Mitzvot, Verses, Reading) :-
+    length(Mitzvot, MCount),
+    length(Verses, VCount),
+    Reading = reading(mitzvot_count(MCount), verse_count(VCount),
+                      grounded_in(Mitzvot, Verses)).