Merge pull request 'fix(learning): כרטיס-אוצֵר כן-3-ערוצים + לכידת ממצאי-אוצֵר (source='curator')' (#339) from worktree-curator-learning-surface into main

mcp-server/src/legal_mcp/server.py

@@ -1176,6 +1176,15 @@ async def list_chair_feedback(
     return await workflow.list_chair_feedback(case_number, category, unresolved_only, _clamp_limit(limit))
 
 
+@mcp.tool()
+async def record_curator_findings(case_number: str, findings: list[dict]) -> str:
+    """לכידת ממצאי-האוצֵר על החלטה סופית כ-decision_lessons מובְנים (source='curator',
+    ממתינים לשער-יו"ר) — INV-LRN3. כל ממצא: {"text": "...", "category": style/structure/
+    lexicon/tabular} (או "tag" עברי). מחזיר כמה נרשמו וכמה כפילויות דולגו. read-only על
+    התוכן — הרישום הצעה הממתינה לאישור דפנה ב-/training, לא שינוי-קול ישיר (G10)."""
+    return await workflow.record_curator_findings(case_number, findings)
+
+
 @mcp.tool()
 async def halacha_corroboration(halacha_id: str) -> dict:
     """החזר את ה-corroboration של הלכה: הציטוטים שמתקפים אותה, הטיפול, וסיכום (X11, read-only)."""

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

@@ -2675,6 +2675,22 @@ async def add_decision_lesson(
     return dict(row) if row else {}
 
 
+async def get_style_corpus_id_by_decision(decision_number: str) -> UUID | None:
+    """Resolve the style_corpus row id for a final decision by its number.
+
+    The curator knows the case_number; lessons attach to the corpus row the
+    learning pipeline enrolled (enroll_style_corpus). Returns None if the final
+    has not been enrolled yet (caller surfaces it — no silent attach).
+    """
+    pool = await get_pool()
+    async with pool.acquire() as conn:
+        row = await conn.fetchrow(
+            "SELECT id FROM style_corpus WHERE decision_number = $1 LIMIT 1",
+            decision_number,
+        )
+    return row["id"] if row else None
+
+
 async def update_decision_lesson(
     lesson_id: UUID,
     *,
@@ -2950,6 +2966,12 @@ async def get_recent_decision_lessons(limit: int = 15, practice_area: str = "")
     Gate (INV-LRN1/G10): returns only CHAIR-APPROVED lessons (review_status='approved').
     Panel-written proposals stay out of the writer's context until the chair approves
     them in /training — the chair's review is the gate, not the panel's 2/2 vote.
+
+    No silent cap (חוקה §6): when more approved lessons match than `limit`, the
+    overflow is dropped by ORDER BY created_at DESC — log it so coverage loss is
+    observable, not invisible. The real fix is lesson synthesis (TaskMaster #158):
+    consolidate overlapping lessons into fewer, richer ones so the set fits without
+    truncation. Until then this WARN is the audit trail.
     """
     pool = await get_pool()
     async with pool.acquire() as conn:
@@ -2964,6 +2986,20 @@ async def get_recent_decision_lessons(limit: int = 15, practice_area: str = "")
                LIMIT $1""",
             limit, practice_area,
         )
+        if len(rows) >= limit:
+            total = await conn.fetchval(
+                """SELECT count(*) FROM decision_lessons dl
+                   JOIN style_corpus sc ON sc.id = dl.style_corpus_id
+                   WHERE dl.review_status = 'approved'
+                     AND ($1 = '' OR sc.practice_area = $1)""",
+                practice_area,
+            ) or 0
+            if total > limit:
+                logger.warning(
+                    "get_recent_decision_lessons: capped %d→%d approved lessons "
+                    "(practice_area=%r) — %d not reaching the writer. See TaskMaster #158 (synthesis).",
+                    total, limit, practice_area or "*", total - limit,
+                )
     return [dict(r) for r in rows]
 
 

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

@@ -403,6 +403,78 @@ async def record_chair_feedback(
     }, message=f"הערה נרשמה בהצלחה. קטגוריה: {category}.")
 
 
+_CURATOR_FINDING_CATEGORIES = {"style", "structure", "lexicon", "tabular", "general"}
+# Agent tags ([סגנון]/[מבנה]/[לקסיקון משפטי]/[טבלאי]) → decision_lessons.category
+_CURATOR_TAG_TO_CATEGORY = {
+    "סגנון": "style", "מבנה": "structure",
+    "לקסיקון משפטי": "lexicon", "לקסיקון": "lexicon", "טבלאי": "tabular",
+}
+
+
+async def record_curator_findings(case_number: str, findings: list[dict]) -> str:
+    """לכידת ממצאי-האוצֵר כ-decision_lessons מובְנים (source='curator', proposed) — INV-LRN3.
+
+    האוצֵר מזהה דפוסי-סגנון בקריאת הסופי; עד כה הם חיו רק כהערה ארעית בערוץ-התגובות
+    (אובד, לא נסקר). כאן הם נתפסים מבנית כך שיופיעו בטאב ״אוצֵר״ ויעברו שער-יו"ר (INV-LRN1/G10).
+    האוצֵר נשאר read-only על התוכן — הרישום הוא הצעה הממתינה לאישור, לא שינוי-קול.
+
+    Args:
+        case_number: מספר התיק הסופי (= decision_number בקורפוס-הסגנון).
+        findings: רשימת ממצאים, כל אחד {"text": "...", "category"/"tag": "..."}.
+                  category ∈ style/structure/lexicon/tabular/general (או tag עברי).
+    """
+    if not findings:
+        return err("findings ריק — אין ממצאים לרשום.")
+    corpus_id = await db.get_style_corpus_id_by_decision(case_number)
+    if not corpus_id:
+        return err(
+            f"לא נמצאה רשומת style_corpus ל-{case_number} — ודא שהסופי נקלט לקורפוס-הסגנון "
+            "(enroll_style_corpus) לפני רישום ממצאים."
+        )
+    # Dedup against lessons already on this corpus (any source) — re-running §A
+    # must not pile duplicates (INV-LRN3 reliability).
+    existing = {(_norm(r["lesson_text"])) for r in await db.list_decision_lessons(corpus_id)}
+    written, skipped_dup, skipped_empty = [], 0, 0
+    for f in findings:
+        text = (f.get("text") or "").strip()
+        if not text:
+            skipped_empty += 1
+            continue
+        if _norm(text) in existing:
+            skipped_dup += 1
+            continue
+        raw_cat = (f.get("category") or f.get("tag") or "general").strip()
+        category = _CURATOR_TAG_TO_CATEGORY.get(raw_cat, raw_cat)
+        if category not in _CURATOR_FINDING_CATEGORIES:
+            category = "general"
+        row = await db.add_decision_lesson(
+            corpus_id,
+            lesson_text=text,
+            category=category,
+            source="curator",
+            created_by="curator",
+            review_status="proposed",
+        )
+        if row:
+            written.append(str(row["id"]))
+            existing.add(_norm(text))
+    return ok({
+        "corpus_id": str(corpus_id),
+        "written": len(written),
+        "skipped_duplicate": skipped_dup,
+        "skipped_empty": skipped_empty,
+        "lesson_ids": written,
+    }, message=(
+        f"נרשמו {len(written)} ממצאי-אוצֵר (source=curator, ממתינים לשער-יו\"ר ב-/training). "
+        f"{skipped_dup} כפילויות דולגו."
+    ))
+
+
+def _norm(s: str) -> str:
+    """Normalize lesson text for dedup — collapse whitespace, strip."""
+    return " ".join((s or "").split())
+
+
 async def list_chair_feedback(
     case_number: str = "",
     category: str = "",