fix(research): עמדת ועדת הערר בטענות-סף נשמרה אך לא נקראה בחזרה

הקורא והכותב של analysis-and-research.md לא הסכימו על מהו שדה: FIELD_LABEL_RE דרש `**כותרת:**` בתחילת שורה, בעוד הכותב התאים את התווית בכל מקום בשורה. האנליסט כותב טענות-סף כרשימה (`- **עמדת ועדת הערר:**`) ואת הסוגיות בתחילת שורה — ולכן שמירה בטענת-סף הצליחה (200 + "✓ נשמר"), אבל הקורא לא ראה את השדה כלל והעמדה נעלמה ברענון. גם יתר שדות הטענה (טענה/תשובה/שאלה משפטית) היו בלתי-נראים באותן טענות. - הקורא מקבל תווית עם סמן-רשימה אופציונלי, כמו הכותב. - הכותב עובר להשתמש באותה הגדרת-גבולות של הקורא (_chair_field_span) במקום regex משלו — `[^*]*?` הישן גם קטע עמדה שהכילה `**הדגשה**`. התווית והסמן נשמרים כפי שהם, וכך גם `---` הסוגר. - תווית מעוטרת (`עמדת ועדת הערר (הכוונת יו"ר 24.6)`) מזוהה בהתאמת-רישא; קודם הכותב הוסיף בלוק כפול במקום לעדכן. - שדה כפול באותו H3 (`### סוגיות 4–6`): הקורא לקח את האחרון והכותב את הראשון. שניהם לוקחים עכשיו את הראשון. - read-after-write: שמירה שהפרסר לא קורא בחזרה מדווחת כשגיאה במקום "נשמר" ירוק, וה-UI שומר בקאש את מה שהשרת קרא — לא את מה ששלח. - תבנית האנליסט (§5) קיבלה שלד מפורש לטענות-סף, זהה לזה של הסוגיות, כדי שקבצים חדשים לא ייווצרו במבנה החורג (נרמול-במקור, G1). הרצת round-trip על כל הקורפוס: 24 מתוך 141 תת-סעיפים נכשלו לפני התיקון (1017, 1019, 1027, 1033, 1043, 1069, 8124) — 0 אחריו. העמדות שכבר נשמרו בקבצים הקיימים חוזרות להיקרא בלי מיגרציה. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-02 14:04:24 +00:00
parent 08419e4434
commit fbdbc64366
5 changed files with 380 additions and 28 deletions
--- a/mcp-server/src/legal_mcp/services/research_md.py
+++ b/mcp-server/src/legal_mcp/services/research_md.py
@@ -43,8 +43,18 @@ SUBSECTION_RE = re.compile(r"^###\s+(.+?)$", re.MULTILINE)
 # Matches "**LABEL:**" field markers — handles both inline and block variants:
 #   "**עמדת המבקשת:** Some text on same line"
 #   "**שאלות משפטיות:**\n1. First question"
+# and both the bare and the list-item form, because the analyst agent writes
+# threshold claims as a bullet list ("- **עמדת ועדת הערר:**") while it writes
+# issues bare. Group 1 is the list marker (or None), group 2 is the label.
 # The label itself must not contain ** or newlines.
-FIELD_LABEL_RE = re.compile(r"^\*\*([^\n*]+?):\*\*[ \t]*", re.MULTILINE)
+FIELD_LABEL_RE = re.compile(
+    r"^([ \t]*(?:[-*+]|\d+[.)])[ \t]+)?\*\*([^\n*]+?):\*\*[ \t]*",
+    re.MULTILINE,
+)
+
+# Terminators that end a field's content even without a following field label:
+# a heading, or a horizontal rule closing the subsection.
+FIELD_TERMINATOR_RE = re.compile(r"^(?:#{2,}[ \t]|[ \t]*---[ \t]*$)", re.MULTILINE)

 # Matches the case number in the H1
 CASE_NUMBER_RE = re.compile(r"#\s*ניתוח.*?ערר\s+([\d/\-]+)", re.MULTILINE)
@@ -53,6 +63,17 @@ CASE_NUMBER_RE = re.compile(r"#\s*ניתוח.*?ערר\s+([\d/\-]+)", re.MULTILIN
 DATE_RE = re.compile(r"^תאריך:\s*(.+?)\s*$", re.MULTILINE)


+def _is_chair_label(label: str) -> bool:
+    """Is this field label the chair-position field?
+
+    Matches on prefix, not equality, because the analyst sometimes decorates the
+    label with a parenthetical — "עמדת ועדת הערר (הכוונת יו"ר 24.6)". Requiring
+    equality made the reader treat those as ordinary fields and the writer append
+    a second, duplicate block instead of updating the existing one.
+    """
+    return label.strip().startswith(CHAIR_POSITION_LABEL)
+
+
 def _is_placeholder(text: str) -> bool:
    """Check if a field value is one of the placeholder strings (empty)."""
    stripped = text.strip()
@@ -135,7 +156,7 @@ def _extract_fields(text: str) -> list[dict]:

    fields = []
    for i, m in enumerate(matches):
-        label = m.group(1).strip()
+        label = m.group(2).strip()
        content_start = m.end()
        content_end = matches[i + 1].start() if i + 1 < len(matches) else len(text)
        content = text[content_start:content_end].strip()
@@ -164,11 +185,17 @@ def _build_subsection_dict(
        parts = title.split(": ", 1)
        display_title = parts[1] if len(parts) > 1 else title

+    # Only the *first* chair-position field is the editable one — the same one
+    # update_chair_position writes to. A subsection that carries more than one
+    # (e.g. an H3 covering "סוגיות 4–6") keeps the extras as ordinary fields
+    # rather than silently reading back a different field than the one saved.
    chair_position = ""
+    chair_seen = False
    regular_fields = []
    for f in fields:
-        if f["label"] == CHAIR_POSITION_LABEL:
+        if not chair_seen and _is_chair_label(f["label"]):
            chair_position = _normalize_chair_position(f["content"])
+            chair_seen = True
        else:
            regular_fields.append(f)

@@ -311,6 +338,46 @@ def _find_subsection_by_id(
    return None


+def _split_trailing_rule(body: str) -> tuple[str, str]:
+    """Split a subsection body into (content, trailing "---" separator).
+
+    Returns ("<body>", "") when the subsection has no closing rule.
+    """
+    m = re.search(r"\n[ \t]*---[ \t]*\s*\Z", body)
+    if not m:
+        return body, ""
+    return body[: m.start()], body[m.start() :]
+
+
+def _chair_field_span(body: str) -> tuple[int, int] | None:
+    """Locate the chair-position field's *content* range in a subsection body.
+
+    Returns (content_start, content_end) — the slice the chair's text occupies,
+    excluding the "**LABEL:**" marker itself so the marker line (and any list
+    bullet in front of it) survives an update untouched. Returns None when the
+    subsection has no chair-position field yet.
+
+    Field boundaries come from FIELD_LABEL_RE — the same definition the reader
+    uses — so what update writes is exactly what parse reads back (G2: one
+    definition of a field, not two that can drift).
+    """
+    matches = list(FIELD_LABEL_RE.finditer(body))
+    for i, m in enumerate(matches):
+        if not _is_chair_label(m.group(2)):
+            continue
+        content_start = m.end()
+        if i + 1 < len(matches):
+            content_end = matches[i + 1].start()
+        else:
+            content_end = len(body)
+        # A heading or closing rule ends the field even without a next label.
+        term = FIELD_TERMINATOR_RE.search(body, content_start, content_end)
+        if term:
+            content_end = term.start()
+        return content_start, content_end
+    return None
+
+
 def update_chair_position(
    file_path: Path, section_id: str, new_text: str
 ) -> dict[str, Any]:
@@ -330,40 +397,62 @@ def update_chair_position(

    _abs_start, _abs_end, subsection_body = found

-    # Find the "**עמדת ועדת הערר:**" label within this subsection
-    label_pattern = re.compile(
-        r"(\*\*" + re.escape(CHAIR_POSITION_LABEL) + r":\*\*)\s*\n?([^*]*?)(?=\n\*\*|\n##|\n---|\Z)",
-        re.DOTALL,
-    )
-    m = label_pattern.search(subsection_body)
-    if not m:
-        # Label not present — append it at the end of the subsection
-        # (just before the trailing --- if any)
-        new_block = f"\n\n**{CHAIR_POSITION_LABEL}:**\n{new_text.strip()}\n"
-        new_subsection = subsection_body.rstrip() + new_block
-        new_content = content[:_abs_start] + new_subsection + content[_abs_end:]
+    span = _chair_field_span(subsection_body)
+    body_text = new_text.strip() or CHAIR_POSITION_PLACEHOLDERS[0]
+
+    if span is None:
+        # Label not present — append it at the end of the subsection,
+        # before a trailing horizontal rule if there is one.
+        head, tail = _split_trailing_rule(subsection_body)
+        new_block = f"\n\n**{CHAIR_POSITION_LABEL}:**\n{body_text}\n"
+        new_subsection = head.rstrip() + new_block + tail
    else:
-        # Replace the existing content of the chair_position field
-        replacement = f"{m.group(1)}\n{new_text.strip() if new_text.strip() else CHAIR_POSITION_PLACEHOLDERS[0]}\n"
+        # Replace the existing content of the chair_position field, keeping the
+        # label line exactly as written (including any list marker) so the file
+        # structure the analyst produced is preserved.
+        content_start, content_end = span
        new_subsection = (
-            subsection_body[: m.start()] + replacement + subsection_body[m.end():]
+            subsection_body[:content_start].rstrip("\r\n \t")
+            + f"\n{body_text}\n"
+            + subsection_body[content_end:]
        )
-        new_content = content[:_abs_start] + new_subsection + content[_abs_end:]
+
+    new_content = content[:_abs_start] + new_subsection + content[_abs_end:]

    # Atomic write
    tmp_path = file_path.with_suffix(file_path.suffix + ".tmp")
    tmp_path.write_text(new_content, encoding="utf-8")  # noqa: STG1 — atomic .tmp; in-place edit, S3 re-sync in Phase-2 read-wiring
    os.replace(tmp_path, file_path)

-    preview = new_text.strip()[:120]
+    # Read-after-write: a position the parser cannot read back is not saved,
+    # however cleanly the write itself succeeded. Reporting success here is what
+    # let a whole class of format drift hide behind a green "נשמר" in the UI.
+    stored = _stored_chair_position(file_path, section_id)
+    expected = _normalize_chair_position(new_text)
+    if stored != expected:
+        raise RuntimeError(
+            f"העמדה נכתבה ל-{file_path.name} אך לא נקראה בחזרה עבור {section_id} "
+            f"— ככל הנראה מבנה השדה בקובץ חורג מהתבנית הצפויה"
+        )
+
    return {
        "saved": True,
        "section_id": section_id,
-        "preview": preview,
+        "position": stored,
+        "preview": stored[:120],
        "timestamp": datetime.now(IL_TZ).isoformat(),
    }


+def _stored_chair_position(file_path: Path, section_id: str) -> str:
+    """Re-parse the file and return the chair position now stored for a section."""
+    parsed = parse(file_path)
+    for item in parsed.get("threshold_claims", []) + parsed.get("issues", []):
+        if item["id"] == section_id:
+            return item.get("chair_position", "") or ""
+    return ""
+
+
 # ── Chair directions extraction (for downstream agents) ─────────