Merge remote-tracking branch 'origin/main' into rebase-357

# Conflicts:
#	mcp-server/src/legal_mcp/services/db.py

mcp-server/src/legal_mcp/services/block_writer.py

@@ -35,29 +35,53 @@ logger = logging.getLogger(__name__)
 
 # ── Block configuration ───────────────────────────────────────────
 
-# Output token limits per Anthropic docs:
-# Opus 4.7: up to 128K output tokens (new tokenizer — ~35% more tokens)
-# Sonnet 4.6: up to 64K output tokens
-# Streaming required when max_tokens > 21,333
+# Generation is structurally deterministic (#204 / WS5): every AI block is
+# pinned to ONE model (Opus 4.8) with a per-block reasoning `effort`. The
+# generation path is claude_session.query → `claude -p` (subscription, near-zero
+# cost; local-only — see reference_claude_generation_path / claude_session
+# docstring). Opus 4.7/4.8 REMOVED temperature/top_p/top_k (sending them → HTTP
+# 400); the only knob is `effort` (low/medium/high/xhigh/max; default high).
+#
+# DEPRECATED FIELDS — DO NOT REINTRODUCE: earlier revisions carried per-block
+# `temp` (0/0.1/0.4) and `model` ("sonnet"/"opus"/"script"). Both were DEAD
+# METADATA: write_block called claude_session.query(prompt, …) WITHOUT model/
+# temp/effort, so generation ran on the CLI's default model with no temperature
+# knob at all (the table only stored a number in decision_blocks.temperature and
+# fed MODEL_MAP→timeout). They are removed here so the table no longer misleads.
+# The conceptual origin (gen_type → thinking-budget) now lives in `effort`; see
+# docs/block-schema.md §3.
+#
+# `gen_type` is retained (documentation/UI metadata + audit `generation_type`).
+# `model` below is the DISPATCH key only: "script" = template-fill (no LLM),
+# "ai" = generated via the pinned Opus model. It is NOT a model alias anymore.
+#
+# Output token note (Anthropic): Opus 4.8 supports large outputs; streaming is
+# handled by the CLI. `max_tokens` is advisory context for callers, not sent.
+GENERATION_MODEL = "claude-opus-4-8"  # single pinned model for every AI block (#204)
+
 BLOCK_CONFIG = {
-    "block-alef": {"index": 1, "title": "כותרת מוסדית", "gen_type": "template-fill", "temp": 0, "model": "script"},
-    "block-bet":  {"index": 2, "title": "הרכב הוועדה", "gen_type": "template-fill", "temp": 0, "model": "script"},
-    "block-gimel":{"index": 3, "title": "צדדים", "gen_type": "template-fill", "temp": 0, "model": "script"},
-    "block-dalet":{"index": 4, "title": "החלטה", "gen_type": "template-fill", "temp": 0, "model": "script"},
-    "block-he":   {"index": 5, "title": "פתיחה", "gen_type": "paraphrase", "temp": 0.2, "model": "sonnet", "max_tokens": 4096},
-    "block-vav":  {"index": 6, "title": "רקע עובדתי", "gen_type": "reproduction", "temp": 0, "model": "sonnet", "max_tokens": 16384},
-    "block-zayin":{"index": 7, "title": "טענות הצדדים", "gen_type": "paraphrase", "temp": 0.1, "model": "sonnet", "max_tokens": 16384},
-    "block-chet": {"index": 8, "title": "הליכים", "gen_type": "reproduction", "temp": 0, "model": "sonnet", "max_tokens": 8192},
-    "block-tet":  {"index": 9, "title": "תכניות חלות", "gen_type": "guided-synthesis", "temp": 0.2, "model": "opus", "max_tokens": 16384},
-    "block-yod":  {"index": 10, "title": "דיון והכרעה", "gen_type": "rhetorical-construction", "temp": 0.4, "model": "opus", "max_tokens": 16384},
-    "block-yod-alef": {"index": 11, "title": "סיכום", "gen_type": "paraphrase", "temp": 0.1, "model": "sonnet", "max_tokens": 8192},
-    "block-yod-bet":  {"index": 12, "title": "חתימות", "gen_type": "template-fill", "temp": 0, "model": "script"},
+    "block-alef": {"index": 1, "title": "כותרת מוסדית", "gen_type": "template-fill", "model": "script"},
+    "block-bet":  {"index": 2, "title": "הרכב הוועדה", "gen_type": "template-fill", "model": "script"},
+    "block-gimel":{"index": 3, "title": "צדדים", "gen_type": "template-fill", "model": "script"},
+    "block-dalet":{"index": 4, "title": "החלטה", "gen_type": "template-fill", "model": "script"},
+    "block-he":   {"index": 5, "title": "פתיחה", "gen_type": "paraphrase", "model": "ai", "effort": "medium", "max_tokens": 4096},
+    "block-vav":  {"index": 6, "title": "רקע עובדתי", "gen_type": "reproduction", "model": "ai", "effort": "medium", "max_tokens": 16384},
+    "block-zayin":{"index": 7, "title": "טענות הצדדים", "gen_type": "paraphrase", "model": "ai", "effort": "high", "max_tokens": 16384},
+    "block-chet": {"index": 8, "title": "הליכים", "gen_type": "reproduction", "model": "ai", "effort": "medium", "max_tokens": 8192},
+    "block-tet":  {"index": 9, "title": "תכניות חלות", "gen_type": "guided-synthesis", "model": "ai", "effort": "high", "max_tokens": 16384},
+    "block-yod":  {"index": 10, "title": "דיון והכרעה", "gen_type": "rhetorical-construction", "model": "ai", "effort": "xhigh", "max_tokens": 16384},
+    "block-yod-alef": {"index": 11, "title": "סיכום", "gen_type": "paraphrase", "model": "ai", "effort": "high", "max_tokens": 8192},
+    "block-yod-bet":  {"index": 12, "title": "חתימות", "gen_type": "template-fill", "model": "script"},
 }
 
-MODEL_MAP = {
-    "sonnet": "claude-sonnet-4-20250514",
-    "opus": "claude-opus-4-7",
-}
+# Default effort when a block lacks an explicit one (defensive; every AI block
+# above sets one). High is the safe default per the generation-path reference.
+DEFAULT_EFFORT = "high"
+
+# Blocks that take longer (deep reasoning) get the LONG timeout. The interim set
+# [he, vav, tet, zayin, chet] and the discussion block all run on the same pinned
+# Opus model, so timeout is driven by effort, not by a model split.
+_LONG_EFFORTS = frozenset({"high", "xhigh", "max"})
 
 
 # ── Template blocks (א-ד, יב) ────────────────────────────────────
@@ -120,11 +144,14 @@ TEMPLATE_WRITERS = {
 BLOCK_PROMPTS = {
     "block-he": """כתוב את בלוק הפתיחה (בלוק ה) של החלטת ועדת ערר.
 
-## כללים:
-- פתח ב"לפנינו ערר..." או "עניינה של החלטה זו..."
-- הגדר "להלן" מרכזיים: הוועדה המקומית, התכנית/הבקשה, המגרש
-- 1-2 סעיפים בלבד
-- אין ניתוח, אין ערכי שיפוט, אין ציטוטים מצדדים
+## מבנה קבוע (חובה — אותו מבנה בכל תיק):
+- **המשפט הראשון פותח תמיד במילה "לפנינו"** — נוסח קבוע: "לפנינו ערר על החלטת
+  [הוועדה המקומית] מיום [תאריך] בעניין [נושא הבקשה/התכנית]." (אל תשתמש ב"עניינה של
+  החלטה זו" או בכל פתיח חלופי — הפתיח אחיד.)
+- סעיף 1: הצגת הערר במשפט הקבוע לעיל + הגדרת ה"להלן" המרכזיים בסדר קבוע:
+  הוועדה המקומית → התכנית/הבקשה → המגרש/המקרקעין.
+- סעיף 2 (רק אם נדרש להשלמת "להלן" נוספים): הגדרות-נוספות בלבד.
+- **בדיוק 1-2 סעיפים.** אין ניתוח, אין ערכי שיפוט, אין ציטוטים מצדדים.
 - מספור: 1.
 
 ## פרטי התיק:
@@ -441,10 +468,19 @@ async def write_block(
             f"Reduce documents or call extract_appraiser_facts first."
         )
 
-    # Call Claude via Claude Code session (no API)
-    model_key = block_cfg["model"]
-    timeout = claude_session.LONG_TIMEOUT if model_key == "opus" else claude_session.DEFAULT_TIMEOUT
-    content = await claude_session.query(prompt, timeout=timeout, tools="")  # prose gen — no tool_use → no error_max_turns
+    # Call Claude via Claude Code session (no API). #204: pin the model + per-block
+    # reasoning effort so generation is structurally deterministic — these were
+    # previously NOT forwarded (the source of inconsistency). model/effort flow
+    # through claude_session.query → `claude -p --model … --effort …`.
+    effort = block_cfg.get("effort", DEFAULT_EFFORT)
+    timeout = claude_session.LONG_TIMEOUT if effort in _LONG_EFFORTS else claude_session.DEFAULT_TIMEOUT
+    content = await claude_session.query(
+        prompt,
+        timeout=timeout,
+        model=GENERATION_MODEL,
+        effort=effort,
+        tools="",  # prose gen — no tool_use → no error_max_turns
+    )
 
     sources = await _collect_block_sources(case_id, block_id)
     sources["case_law_ids"] = _precedent_case_law_ids
@@ -455,6 +491,7 @@ async def write_block(
 
 def _build_result(block_id: str, content: str, block_cfg: dict) -> dict:
     word_count = len(content.split())
+    is_ai = block_cfg["model"] == "ai"
     return {
         "block_id": block_id,
         "block_index": block_cfg["index"],
@@ -462,8 +499,14 @@ def _build_result(block_id: str, content: str, block_cfg: dict) -> dict:
         "content": content,
         "word_count": word_count,
         "generation_type": block_cfg["gen_type"],
-        "model_used": block_cfg["model"],
-        "temperature": block_cfg["temp"],
+        # AI blocks record the pinned model; template blocks record "script".
+        "model_used": GENERATION_MODEL if is_ai else block_cfg["model"],
+        # The real generation knob (#204). None for template/script blocks.
+        "effort": block_cfg.get("effort", DEFAULT_EFFORT) if is_ai else None,
+        # DEPRECATED: temperature is not a real knob on Opus 4.7/4.8 (sending it
+        # → HTTP 400). Kept only to satisfy decision_blocks.temperature
+        # NUMERIC(3,2); always 0. Read `effort` instead.
+        "temperature": 0,
     }
 
 

mcp-server/src/legal_mcp/services/db.py

@@ -18,6 +18,43 @@ from legal_mcp.services import court_citation, halacha_quality, principles
 
 logger = logging.getLogger(__name__)
 
+# ── Primary-document classification (WS2 / task #200) ────────────────
+# Canonical, single-source list of "primary" (מסמך עיקרי) doc_types — the
+# substantive case documents the chair tracks for analysis (appeal, the
+# replies/objections, the hearing protocol, the appraisal, and the
+# committee decision). Every OTHER doc_type (plan, permit, court_decision,
+# exhibit, reference…) is secondary. Chair-approved set (plan WS2 §1).
+#
+# G1/G2/INV-DM7: `is_primary` is DERIVED from `doc_type`, never an
+# independently-written column. There is ONE source of truth: this tuple.
+# The DB column `documents.is_primary` is a GENERATED ALWAYS … STORED column
+# (V47) computed by Postgres from `doc_type`, so it can never drift; the
+# Python helper below mirrors the same list for read-time derivation and for
+# building the generated-column expression. No parallel write path.
+PRIMARY_DOC_TYPES: tuple[str, ...] = (
+    "appeal",      # כתב-ערר
+    "response",    # תשובה / תגובה
+    "objection",   # התנגדות
+    "protocol",    # פרוטוקול-דיון
+    "appraisal",   # שומה
+    "decision",    # החלטת-ועדה
+)
+
+
+def is_primary_doc_type(doc_type: str | None) -> bool:
+    """Whether a doc_type is a 'primary' (מסמך עיקרי) document. Single source
+    of truth = PRIMARY_DOC_TYPES; mirrors the V47 generated column."""
+    return doc_type in PRIMARY_DOC_TYPES
+
+
+def _primary_doc_types_sql_array() -> str:
+    """SQL ARRAY[...] literal of PRIMARY_DOC_TYPES for the generated column.
+    Values are fixed identifiers from this module (no user input) — safe to
+    inline; kept derived from the tuple so the list has ONE definition."""
+    quoted = ", ".join("'" + t.replace("'", "''") + "'" for t in PRIMARY_DOC_TYPES)
+    return f"ARRAY[{quoted}]::text[]"
+
+
 _pool: asyncpg.Pool | None = None
 _schema_ready: bool = False
 _init_lock: asyncio.Lock = asyncio.Lock()
@@ -1782,7 +1819,23 @@ CREATE INDEX IF NOT EXISTS idx_decision_lessons_vec
     ON decision_lessons USING ivfflat (embedding vector_cosine_ops) WITH (lists = 30);
 """
 
-# ── V47: Protocol comparative analysis (WS4 / #203) ───────────────
+# V47 (WS2 / task #200): "primary document" (מסמך עיקרי) concept.
+# `documents.is_primary` is a GENERATED ALWAYS … STORED column derived purely
+# from `doc_type` against the canonical PRIMARY_DOC_TYPES list (built from the
+# single-source tuple via _primary_doc_types_sql_array). Because Postgres
+# computes it, there is NO parallel write path and it can never drift from
+# doc_type (G1/G2/INV-DM7 — same drift-free pattern as the GENERATED tsvectors,
+# INV-DM3). Idempotent: ADD COLUMN IF NOT EXISTS; the generated expression is
+# fixed, so re-running is a no-op. The partial index serves the
+# "primary docs not yet analysed" queries that #201 builds on.
+SCHEMA_V47_SQL = f"""
+ALTER TABLE documents ADD COLUMN IF NOT EXISTS is_primary BOOLEAN
+    GENERATED ALWAYS AS (doc_type = ANY({_primary_doc_types_sql_array()})) STORED;
+CREATE INDEX IF NOT EXISTS idx_documents_primary
+    ON documents(case_id) WHERE is_primary;
+"""
+
+# ── V48: Protocol comparative analysis (WS4 / #203) ───────────────
 #
 # protocol_analysis: case-knowledge derived from a hearing-protocol document by
 # comparing the oral arguments raised at the hearing against the written
@@ -1798,7 +1851,7 @@ CREATE INDEX IF NOT EXISTS idx_decision_lessons_vec
 # back to the canonical `cases` columns (panel via decisions, hearing_date on
 # cases) — NOT duplicated here — and a copy of the raw extracted feed is kept on
 # the analysis row for provenance only (G9).
-SCHEMA_V47_SQL = """
+SCHEMA_V48_SQL = """
 CREATE TABLE IF NOT EXISTS protocol_analysis (
     id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
     case_id UUID NOT NULL REFERENCES cases(id) ON DELETE CASCADE,
@@ -1887,6 +1940,7 @@ async def _apply_schema_ddl(conn: asyncpg.Connection) -> None:
         await conn.execute(SCHEMA_V45_SQL)
         await conn.execute(SCHEMA_V46_SQL)
         await conn.execute(SCHEMA_V47_SQL)
+        await conn.execute(SCHEMA_V48_SQL)
 
 
 async def init_schema() -> None:
@@ -2259,6 +2313,14 @@ def _row_to_doc(row: asyncpg.Record) -> dict:
     d["case_id"] = str(d["case_id"])
     if isinstance(d.get("metadata"), str):
         d["metadata"] = json.loads(d["metadata"])
+    # Primary/secondary classification (WS2 / #200). `is_primary` is the
+    # generated DB column (V47); derive it at read-time too so the field is
+    # always present even on rows fetched before the migration ran, and expose
+    # a human-facing `doc_category`. Single source of truth: PRIMARY_DOC_TYPES.
+    is_primary = bool(d["is_primary"]) if d.get("is_primary") is not None \
+        else is_primary_doc_type(d.get("doc_type"))
+    d["is_primary"] = is_primary
+    d["doc_category"] = "primary" if is_primary else "secondary"
     return d
 
 
@@ -4003,7 +4065,7 @@ async def detect_appraiser_conflicts(case_id: UUID) -> list[dict]:
     return conflicts
 
 
-# ── Protocol comparative analysis (V47 / WS4 #203) ────────────────
+# ── Protocol comparative analysis (V48 / WS4 #203) ────────────────
 
 async def replace_protocol_analysis(
     case_id: UUID,

mcp-server/src/legal_mcp/tools/documents.py

@@ -264,6 +264,11 @@ async def document_get_text(case_number: str, doc_title: str = "") -> str:
 async def document_list(case_number: str) -> str:
     """רשימת מסמכים בתיק.
 
+    כל מסמך כולל `doc_type`, וכן את הסיווג הנגזר `is_primary` (bool) ו-
+    `doc_category` ("primary"/"secondary") — מסמך-עיקרי (ערר/תשובה/התנגדות/
+    פרוטוקול/שומה/החלטת-ועדה) מול משני. נגזר מ-`doc_type` (db.PRIMARY_DOC_TYPES),
+    אינו נכתב ידנית.
+
     Args:
         case_number: מספר תיק הערר
     """

mcp-server/src/legal_mcp/tools/drafting.py

@@ -516,9 +516,18 @@ async def export_docx(case_number: str, output_path: str = "") -> str:
 
 # ── Interim draft (pre-ruling) ────────────────────────────────────
 
-# Blocks written for the interim draft, in display order.
+# Blocks written for the interim draft, in a FIXED order.
 # This is the same content the chair sees in the final decision (same template,
-# same skill, same prompts) — minus opening, ruling, summary, signatures.
+# same skill, same prompts, same single canonical write path — block_writer) —
+# minus ruling, summary, signatures.
+#
+# Determinism (#204 / WS5): the interim draft is STRUCTURALLY deterministic.
+# Each block is generated by block_writer.write_block, which now pins the model
+# (Opus 4.8) and a per-block reasoning effort, and uses fixed structural prompts
+# (e.g. block-he's opening is always "לפנינו ערר…"). The display order on export
+# is fixed separately by docx_exporter._INTERIM_BLOCK_ORDER. There is no parallel
+# generation path (G2): write_interim_draft is a thin orchestrator over the same
+# write_and_store_block used by the full decision.
 _INTERIM_BLOCKS = ["block-he", "block-vav", "block-tet", "block-zayin", "block-chet"]